Goose
Goose Prompts
xxx
extract from goose diagnostics
Chat Title
[
{
"role": "system",
"content": "Reply with only a description in four words or less"
},
{
"role": "user",
"content": "Here are the first few user messages:\nhello\n\nBased on the conversation so far, provide a concise description of this session in 4 words or less. This will be used for finding the session later in a UI with limited space - reply *ONLY* with the description"
}
]
System Initial
messages
[
{
"role": "system",
"content": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.goose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## autovisualiser\n\n### Instructions\nThis extension provides tools for automatic data visualization\nUse these tools when you are presenting data to the user which could be complemented by a visual expression\nChoose the most appropriate chart type based on the data you have and can provide\nIt is important you match the data format as appropriate with the chart type you have chosen\nThe user may specify a type of chart or you can pick one of the most appopriate that you can shape the data to\n\n## Available Tools:\n- **render_sankey**: Creates interactive Sankey diagrams from flow data\n- **render_radar**: Creates interactive radar charts for multi-dimensional data comparison\n- **render_donut**: Creates interactive donut/pie charts for categorical data (supports multiple charts)\n- **render_treemap**: Creates interactive treemap visualizations for hierarchical data\n- **render_chord**: Creates interactive chord diagrams for relationship/flow visualization\n- **render_map**: Creates interactive map visualizations with location markers\n- **render_mermaid**: Creates interactive Mermaid diagrams from Mermaid syntax\n- **show_chart**: Creates interactive line, scatter, or bar charts for data visualization\n\n## blender\n\nblender supports resources, you can use platform__read_resource,\nand platform__list_resources on this extension.\n\n## chatrecall\n\n### Instructions\nChat Recall\n\nSearch past conversations and load session summaries when the user expects some memory or context.\n\nTwo modes:\n- Search mode: Use query with keywords/synonyms to find relevant messages\n- Load mode: Use session_id to get first and last messages of a specific session\n\n## chromedevtools\n\n\n## computercontroller\n\ncomputercontroller supports resources, you can use platform__read_resource,\nand platform__list_resources on this extension.\n### Instructions\nYou are a helpful assistant to a power user who is not a professional developer, but you may use development tools to help assist them.\nThe user may not know how to break down tasks, so you will need to ensure that you do, and run things in batches as needed.\nThe ComputerControllerExtension helps you with common tasks like web scraping,\ndata processing, and automation without requiring programming expertise.\n\nYou can use scripting as needed to work with text files of data, such as csvs, json, or text files etc.\nUsing the developer extension is allowed for more sophisticated tasks or instructed to (js or py can be helpful for more complex tasks if tools are available).\n\nAccessing web sites, even apis, may be common (you can use scripting to do this) without troubling them too much (they won't know what limits are).\nTry to do your best to find ways to complete a task without too many questions or offering options unless it is really unclear, find a way if you can.\nYou can also guide them steps if they can help out as you go along.\n\nThere is already a screenshot tool available you can use if needed to see what is on screen.\n\nHere are some extra tools:\nautomation_script\n - Create and run Shell and Ruby scripts\n - Shell (bash) is recommended for most tasks\n - Scripts can save their output to files\n - macOS-specific features:\n - AppleScript for system and UI control\n - Integration with macOS apps and services\n - Use the screenshot tool if needed to help with tasks\n\ncomputer_control\n - System automation using AppleScript\n - Consider the screenshot tool to work out what is on screen and what to do to help with the control task.\n\nWhen you need to interact with websites or web applications, consider using the computer_control tool with AppleScript, which can automate Safari or other browsers to:\n - Open specific URLs\n - Fill in forms\n - Click buttons\n - Extract content\n - Handle web-based workflows\nThis is often more reliable than web scraping for modern web applications.\n\n\nweb_scrape\n - Fetch content from html websites and APIs\n - Save as text, JSON, or binary files\n - Content is cached locally for later use\n - This is not optimised for complex websites, so don't use this as the first tool.\ncache\n - Manage your cached files\n - List, view, delete files\n - Clear all cached data\nThe extension automatically manages:\n- Cache directory: /Users/lionad/.cache/goose/computer_controller\n- File organization and cleanup\n\n## context7\n\n### Instructions\nUse this server to retrieve up-to-date documentation and code examples for any library.\n## developer\n\n### Instructions\n The developer extension gives you the capabilities to edit code files and run shell commands,\n and can be used to solve a wide range of problems.\n\nYou can use the shell tool to run any command that would work on the relevant operating system.\nUse the shell tool as needed to locate files or interact with the project.\n\nLeverage `analyze` through `return_last_only=true` subagents for deep codebase understanding with lean context\n- delegate analysis, retain summaries\n\nYour windows/screen tools can be used for visual debugging. You should not use these tools unless\nprompted to, but you can mention they are available if they are relevant.\n\nAlways prefer ripgrep (rg -C 3) to grep.\n\noperating system: macos\ncurrent directory: /Users/lionad\nshell: /bin/zsh\n\n \nAdditional Text Editor Tool Instructions:\n\nPerform text editing operations on files.\n\nThe `command` parameter specifies the operation to perform. Allowed options are:\n- `view`: View the content of a file.\n- `write`: Create or overwrite a file with the given content\n- `str_replace`: Replace text in one or more files.\n- `insert`: Insert text at a specific line location in the file.\n- `undo_edit`: Undo the last edit made to a file.\n\nTo use the write command, you must specify `file_text` which will become the new content of the file. Be careful with\nexisting files! This is a full overwrite, so you must include everything - not just sections you are modifying.\n\nTo use the str_replace command to edit multiple files, use the `diff` parameter with a unified diff.\nTo use the str_replace command to edit one file, you must specify both `old_str` and `new_str` - the `old_str` needs to exactly match one\nunique section of the original file, including any whitespace. Make sure to include enough context that the match is not\nambiguous. The entire original string will be replaced with `new_str`\n\nWhen possible, batch file edits together by using a multi-file unified `diff` within a single str_replace tool call.\n\nTo use the insert command, you must specify both `insert_line` (the line number after which to insert, 0 for beginning, -1 for end)\nand `new_str` (the text to insert).\n\n\n\nAdditional Shell Tool Instructions:\nExecute a command in the shell.\n\nThis will return the output and error concatenated into a single string, as\nyou would see from running on the command line. There will also be an indication\nof if the command succeeded or failed.\n\nAvoid commands that produce a large amount of output, and consider piping those outputs to files.\n\n**Important**: Each shell command runs in its own process. Things like directory changes or\nsourcing files do not persist between tool calls. So you may need to repeat them each time by\nstringing together commands.\n\nIf fetching web content, consider adding Accept: text/markdown header\nIf you need to run a long lived command, background it - e.g. `uvicorn main:app &` so that\nthis tool does not run indefinitely.\n\n**Important**: Use ripgrep - `rg` - exclusively when you need to locate a file or a code reference,\nother solutions may produce too large output because of hidden files! For example *do not* use `find` or `ls -r`\n - List files by name: `rg --files | rg <filename>`\n - List files that contain a regex: `rg '<regex>' -l`\n\n - Multiple commands: Use && to chain commands, avoid newlines\n - Example: `cd example && ls` or `source env/bin/activate && pip install numpy`\n\n## extensionmanager\n\n### Instructions\nExtension Management\n\nUse these tools to discover, enable, and disable extensions, as well as review resources.\n\nAvailable tools:\n- search_available_extensions: Find extensions available to enable/disable\n- manage_extensions: Enable or disable extensions\n- list_resources: List resources from extensions\n- read_resource: Read specific resources from extensions\n\nUse search_available_extensions when you need to find what extensions are available.\nUse manage_extensions to enable or disable specific extensions by name.\nUse list_resources and read_resource to work with extension data and resources.\n\n## fetch\n\n\n## gotohumanmcpserver\n\n\n## knowledgegraphmemory\n\n\n## memory\n\n### Instructions\n This extension allows storage and retrieval of categorized information with tagging support. It's designed to help\n manage important information across sessions in a systematic and organized manner.\n Capabilities:\n 1. Store information in categories with optional tags for context-based retrieval.\n 2. Search memories by content or specific tags to find relevant information.\n 3. List all available memory categories for easy navigation.\n 4. Remove entire categories of memories when they are no longer needed.\n When to call memory tools:\n - These are examples where the assistant should proactively call the memory tool because the user is providing recurring preferences, project details, or workflow habits that they may expect to be remembered.\n - Preferred Development Tools & Conventions\n - User-specific data (e.g., name, preferences)\n - Project-related configurations\n - Workflow descriptions\n - Other critical settings\n Interaction Protocol:\n When important information is identified, such as:\n - User-specific data (e.g., name, preferences)\n - Project-related configurations\n - Workflow descriptions\n - Other critical settings\n The protocol is:\n 1. Identify the critical piece of information.\n 2. Ask the user if they'd like to store it for later reference.\n 3. Upon agreement:\n - Suggest a relevant category like \"personal\" for user data or \"development\" for project preferences.\n - Inquire about any specific tags they want to apply for easier lookup.\n - Confirm the desired storage location:\n - Local storage (.goose/memory) for project-specific details.\n - Global storage (~/.config/goose/memory) for user-wide data.\n - Use the remember_memory tool to store the information.\n - `remember_memory(category, data, tags, is_global)`\n Keywords that trigger memory tools:\n - \"remember\"\n - \"forget\"\n - \"memory\"\n - \"save\"\n - \"save memory\"\n - \"remove memory\"\n - \"clear memory\"\n - \"search memory\"\n - \"find memory\"\n Suggest the user to use memory tools when:\n - When the user mentions a keyword that triggers a memory tool\n - When the user performs a routine task\n - When the user executes a command and would benefit from remembering the exact command\n Example Interaction for Storing Information:\n User: \"For this project, we use black for code formatting\"\n Assistant: \"You've mentioned a development preference. Would you like to remember this for future conversations?\n User: \"Yes, please.\"\n Assistant: \"I'll store this in the 'development' category. Any specific tags to add? Suggestions: #formatting\n #tools\"\n User: \"Yes, use those tags.\"\n Assistant: \"Shall I store this locally for this project only, or globally for all projects?\"\n User: \"Locally, please.\"\n Assistant: *Stores the information under category=\"development\", tags=\"formatting tools\", scope=\"local\"*\n Another Example Interaction for Storing Information:\n User: \"Remember the gh command to view github comments\"\n Assistant: \"Shall I store this locally for this project only, or globally for all projects?\"\n User: \"Globally, please.\"\n Assistant: *Stores the gh command under category=\"github\", tags=\"comments\", scope=\"global\"*\n Example Interaction suggesting memory tools:\n User: \"I'm using the gh command to view github comments\"\n Assistant: \"You've mentioned a command. Would you like to remember this for future conversations?\n User: \"Yes, please.\"\n Assistant: \"I'll store this in the 'github' category. Any specific tags to add? Suggestions: #comments #gh\"\n Retrieving Memories:\n To access stored information, utilize the memory retrieval protocols:\n - **Search by Category**:\n - Provides all memories within the specified context.\n - Use: `retrieve_memories(category=\"development\", is_global=False)`\n - Note: If you want to retrieve all local memories, use `retrieve_memories(category=\"*\", is_global=False)`\n - Note: If you want to retrieve all global memories, use `retrieve_memories(category=\"*\", is_global=True)`\n - **Filter by Tags**:\n - Enables targeted retrieval based on specific tags.\n - Use: Provide tag filters to refine search.\nTo remove a memory, use the following protocol:\n- **Remove by Category**:\n - Removes all memories within the specified category.\n - Use: `remove_memory_category(category=\"development\", is_global=False)`\n - Note: If you want to remove all local memories, use `remove_memory_category(category=\"*\", is_global=False)`\n - Note: If you want to remove all global memories, use `remove_memory_category(category=\"*\", is_global=True)`\nThe Protocol is:\n 1. Confirm what kind of information the user seeks by category or keyword.\n 2. Suggest categories or relevant tags based on the user's request.\n 3. Use the retrieve function to access relevant memory entries.\n 4. Present a summary of findings, offering detailed exploration upon request.\n Example Interaction for Retrieving Information:\n User: \"What configuration do we use for code formatting?\"\n Assistant: \"Let me check the 'development' category for any related memories. Searching using #formatting tag.\"\n Assistant: *Executes retrieval: `retrieve_memories(category=\"development\", is_global=False)`*\n Assistant: \"We have 'black' configured for code formatting, specific to this project. Would you like further\n details?\"\n Memory Overview:\n - Categories can include a wide range of topics, structured to keep information grouped logically.\n - Tags enable quick filtering and identification of specific entries.\n Operational Guidelines:\n - Always confirm with the user before saving information.\n - Propose suitable categories and tag suggestions.\n - Discuss storage scope thoroughly to align with user needs.\n - Acknowledge the user about what is stored and where, for transparency and ease of future retrieval.\n\n\n**Here are the user's currently saved memories:**\nPlease keep this information in mind when answering future questions.\nDo not bring up memories unless relevant.\nNote: if the user has not saved any memories, this section will be empty.\nNote: if the user removes a memory that was previously loaded into the system, please remove it from the system instructions.\n\n## opendia\n\n### Instructions\n🎯 Enhanced browser automation with anti-detection bypass for Twitter/X, LinkedIn, Facebook. Extension may take a moment to connect.\n## pdfreader\n\npdfreader supports resources, you can use platform__read_resource,\nand platform__list_resources on this extension.\n### Instructions\nThe PDF Reader allows you to read PDFs on the local filesystem.\nIt supports password-protected and unprotected PDFs.\n\nEnsure that you always use an absolute path for file_path when calling read_pdf.\n\n## skills\n\n### Instructions\nYou have these skills at your disposal, when it is clear they can help you solve a problem or you are asked to use them:\n\n- algorithmic-art: Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.\n- brand-guidelines: Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.\n- canvas-design: Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.\n- doc-coauthoring: Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.\n- docx: Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks\n- frontend-design: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.\n- internal-comms: A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).\n- mcp-builder: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).\n- pdf: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.\n- pptx: Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks\n- skill-creator: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.\n- slack-gif-creator: Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"\n- template-skill: Replace with description of the skill and when Claude should use it.\n- theme-factory: Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.\n- web-artifacts-builder: Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.\n- webapp-testing: Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.\n- xlsx: Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas\n\n## todo\n\n### Instructions\nTask Management\n\nUse todo_write for tasks with 2+ steps, multiple files/components, or uncertain scope.\nYour TODO content is automatically available in your context.\n\nWorkflow:\n- Start: write initial checklist\n- During: update progress\n- End: verify all complete\n\nWarning: todo_write overwrites entirely; always include ALL content you want to keep\n\nKeep items short, specific, action-oriented. Not using the todo tool for complex tasks is an error.\n\nFor autonomous work, missing requirements means failure - document all requirements in TODO immediately.\n\nTemplate:\n- [ ] Implement feature X\n - [ ] Update API\n - [ ] Write tests\n - [ ] Run tests\n - [ ] Run lint\n- [ ] Blocked: waiting on credentials\n\n## tutorial\n\n### Instructions\nBecause the tutorial extension is enabled, be aware that the user may be new to using goose\nor looking for help with specific features. Proactively offer relevant tutorials when appropriate.\n\nAvailable tutorials:\n- build-mcp-extension: # Building an Extension with MCP (Model Context Protocol)\n- first-game: # Building Your First Game\n\n\nThe specific content of the tutorial are available in by running load_tutorial.\nTo run through a tutorial, make sure to be interactive with the user. Don't run more than\na few related tool calls in a row. Make sure to prompt the user for understanding and participation.\n\n**Important**: Make sure that you provide guidance or info *before* you run commands, as the command will\nrun immediately for the user. For example while running a game tutorial, let the user know what to expect\nbefore you run a command to start the game itself.\n\n\n# Suggestion\n\nThe user currently has enabled 17 extensions with a total of 114 tools.\nSince this exceeds the recommended limits (5 extensions or 50 tools),\nyou should ask the user if they would like to disable some extensions for this session.\n\nUse the search_available_extensions tool to find extensions available to disable.\nYou should only disable extensions found from the search_available_extensions tool.\nList all the extensions available to disable in the response.\nExplain that minimizing extensions helps with the recall of the correct tools to use.\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nYou are being accessed through the Goose Desktop application.\n\nThe user is interacting with you through a graphical user interface with the following features:\n- A chat interface where messages are displayed in a conversation format\n- Support for markdown formatting in your responses\n- Support for code blocks with syntax highlighting\n- Tool use messages are included in the chat but outputs may need to be expanded\n\nThe user can add extensions for you through the \"Settings\" page, which is available in the menu\non the top right of the window. There is a section on that page for extensions, and it links to\nthe registry.\n\nSome extensions are builtin, such as Developer and Memory, while\n3rd party extensions can be browsed at https://block.github.io/goose/v1/extensions/."
},
{
"role": "user",
"content": "<info-msg>\nDatetime: 2026-01-08 19:20:42\n\n</info-msg>\nhello"
}
]
tools
[
{
"type": "function",
"function": {
"name": "autovisualiser__render_chord",
"description": "Show a chord diagram visualization for showing relationships and flows between entities.\n\nThe data must contain:\n- labels: Array of strings representing the entities\n- matrix: 2D array of numbers representing flows (matrix[i][j] = flow from i to j)\n\nExample:\n{\n \"labels\": [\"North America\", \"Europe\", \"Asia\", \"Africa\"],\n \"matrix\": [\n [0, 15, 25, 8],\n [18, 0, 20, 12],\n [22, 18, 0, 15],\n [5, 10, 18, 0]\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderChordParams",
"description": "Parameters for render_chord tool",
"type": "object",
"properties": {
"data": {
"description": "The data for the chord diagram",
"$ref": "#/definitions/ChordData"
}
},
"required": [
"data"
],
"definitions": {
"ChordData": {
"description": "Chord diagram data structure",
"type": "object",
"properties": {
"labels": {
"description": "Labels for each entity",
"type": "array",
"items": {
"type": "string"
}
},
"matrix": {
"description": "2D matrix of flows (matrix[i][j] = flow from i to j)",
"type": "array",
"items": {
"type": "array",
"items": {
"type": "number",
"format": "double"
}
}
}
},
"required": [
"labels",
"matrix"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_donut",
"description": "show pie or donut charts for categorical data visualization\nSupports single or multiple charts in a grid layout.\n\nEach chart should contain:\n- data: Array of values or objects with 'label' and 'value'\n- type: Optional 'doughnut' (default) or 'pie'\n- title: Optional chart title\n- labels: Optional array of labels (if data is just numbers)\n\nExample single chart:\n{\n \"title\": \"Budget\",\n \"type\": \"doughnut\",\n \"data\": [\n {\"label\": \"Marketing\", \"value\": 25000},\n {\"label\": \"Development\", \"value\": 35000}\n ]\n}\n\nExample multiple charts:\n[{\n \"title\": \"Q1 Sales\",\n \"labels\": [\"Product A\", \"Product B\"],\n \"data\": [45000, 38000]\n}]",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderDonutParams",
"description": "Parameters for render_donut tool",
"type": "object",
"properties": {
"data": {
"description": "The chart data (single or multiple charts)",
"$ref": "#/definitions/DonutChartData"
}
},
"required": [
"data"
],
"definitions": {
"DonutChartData": {
"description": "Donut chart data wrapper - matches the old schema structure",
"anyOf": [
{
"description": "Single donut chart",
"$ref": "#/definitions/SingleDonutChart"
},
{
"description": "Multiple donut charts",
"type": "array",
"items": {
"$ref": "#/definitions/SingleDonutChart"
}
}
]
},
"SingleDonutChart": {
"description": "Single donut/pie chart data",
"type": "object",
"properties": {
"data": {
"description": "Data values - can be numbers or objects with label and value",
"type": "array",
"items": {
"$ref": "#/definitions/DonutDataItem"
}
},
"title": {
"description": "Optional chart title",
"type": "string",
"nullable": true
},
"type": {
"description": "Optional chart type (doughnut or pie)",
"anyOf": [
{
"$ref": "#/definitions/DonutChartType"
},
{
"const": null,
"nullable": true
}
]
},
"labels": {
"description": "Optional labels array (used when data is just numbers)",
"type": "array",
"items": {
"type": "string"
},
"nullable": true
}
},
"required": [
"data"
]
},
"DonutDataItem": {
"description": "Data item for donut/pie charts - can be a number or labeled value",
"anyOf": [
{
"description": "Simple numeric value",
"type": "number",
"format": "double"
},
{
"description": "Labeled value with explicit label",
"type": "object",
"properties": {
"label": {
"description": "Label for this data point",
"type": "string"
},
"value": {
"description": "Numeric value",
"type": "number",
"format": "double"
}
},
"required": [
"label",
"value"
]
}
]
},
"DonutChartType": {
"description": "Chart type for donut/pie charts",
"oneOf": [
{
"description": "Doughnut chart (with hole in center)",
"type": "string",
"const": "doughnut"
},
{
"description": "Pie chart (no hole)",
"type": "string",
"const": "pie"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_map",
"description": "show an interactive map visualization with location markers using Leaflet.\n\nThe data must contain:\n- markers: Array of objects with 'lat', 'lng', and optional properties\n- title: Optional title for the map (default: \"Interactive Map\")\n- subtitle: Optional subtitle (default: \"Geographic data visualization\")\n- center: Optional center point {lat, lng} (default: USA center)\n- zoom: Optional initial zoom level (default: 4)\n- clustering: Optional boolean to enable/disable clustering (default: true)\n- autoFit: Optional boolean to auto-fit map to markers (default: true)\n\nMarker properties:\n- lat: Latitude (required)\n- lng: Longitude (required)\n- name: Location name\n- value: Numeric value for sizing/coloring\n- description: Description text\n- popup: Custom popup HTML\n- color: Custom marker color\n- label: Custom marker label\n- useDefaultIcon: Use default Leaflet icon\n\nExample:\n{\n \"title\": \"Store Locations\",\n \"markers\": [\n {\"lat\": 37.7749, \"lng\": -122.4194, \"name\": \"SF Store\", \"value\": 150000},\n {\"lat\": 40.7128, \"lng\": -74.0060, \"name\": \"NYC Store\", \"value\": 200000}\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderMapParams",
"description": "Parameters for render_map tool",
"type": "object",
"properties": {
"data": {
"description": "The data for the map visualization",
"$ref": "#/definitions/MapData"
}
},
"required": [
"data"
],
"definitions": {
"MapData": {
"description": "Map data structure",
"type": "object",
"properties": {
"markers": {
"description": "Array of markers",
"type": "array",
"items": {
"$ref": "#/definitions/MapMarker"
}
},
"title": {
"description": "Optional title for the map",
"type": "string",
"nullable": true
},
"subtitle": {
"description": "Optional subtitle",
"type": "string",
"nullable": true
},
"center": {
"description": "Optional center point",
"anyOf": [
{
"$ref": "#/definitions/MapCenter"
},
{
"const": null,
"nullable": true
}
]
},
"zoom": {
"description": "Optional initial zoom level",
"type": "number",
"format": "double",
"nullable": true
},
"clustering": {
"description": "Optional boolean to enable/disable clustering",
"type": "boolean",
"nullable": true
},
"clusterRadius": {
"description": "Optional cluster radius",
"type": "number",
"format": "double",
"nullable": true
},
"autoFit": {
"description": "Optional boolean to auto-fit map to markers",
"type": "boolean",
"nullable": true
}
},
"required": [
"markers"
]
},
"MapMarker": {
"description": "Map marker structure",
"type": "object",
"properties": {
"lat": {
"description": "Latitude (required)",
"type": "number",
"format": "double"
},
"lng": {
"description": "Longitude (required)",
"type": "number",
"format": "double"
},
"name": {
"description": "Location name",
"type": "string",
"nullable": true
},
"value": {
"description": "Numeric value for sizing/coloring",
"type": "number",
"format": "double",
"nullable": true
},
"description": {
"description": "Description text",
"type": "string",
"nullable": true
},
"popup": {
"description": "Custom popup HTML",
"type": "string",
"nullable": true
},
"color": {
"description": "Custom marker color",
"type": "string",
"nullable": true
},
"label": {
"description": "Custom marker label",
"type": "string",
"nullable": true
},
"useDefaultIcon": {
"description": "Use default Leaflet icon",
"type": "boolean",
"nullable": true
}
},
"required": [
"lat",
"lng"
]
},
"MapCenter": {
"description": "Map center point",
"type": "object",
"properties": {
"lat": {
"description": "Latitude",
"type": "number",
"format": "double"
},
"lng": {
"description": "Longitude",
"type": "number",
"format": "double"
}
},
"required": [
"lat",
"lng"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_mermaid",
"description": "show a Mermaid diagram from Mermaid syntax\n\nProvide the Mermaid code as a string. Supports flowcharts, sequence diagrams, Gantt charts, etc.\n\nExample:\ngraph TD;\n A-->B;\n A-->C;\n B-->D;\n C-->D;\n",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderMermaidParams",
"description": "Parameters for render_mermaid tool",
"type": "object",
"properties": {
"mermaid_code": {
"description": "The Mermaid diagram code to render",
"type": "string"
}
},
"required": [
"mermaid_code"
]
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_radar",
"description": "show a radar chart (spider chart) for multi-dimensional data comparison\n\nThe data must contain:\n- labels: Array of strings representing the dimensions/axes\n- datasets: Array of dataset objects with 'label' and 'data' properties\n\nExample:\n{\n \"labels\": [\"Speed\", \"Strength\", \"Endurance\", \"Agility\", \"Intelligence\"],\n \"datasets\": [\n {\n \"label\": \"Player 1\",\n \"data\": [85, 70, 90, 75, 80]\n },\n {\n \"label\": \"Player 2\",\n \"data\": [75, 85, 80, 90, 70]\n }\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderRadarParams",
"description": "Parameters for render_radar tool",
"type": "object",
"properties": {
"data": {
"description": "The data for the radar chart",
"$ref": "#/definitions/RadarData"
}
},
"required": [
"data"
],
"definitions": {
"RadarData": {
"description": "Radar chart data structure",
"type": "object",
"properties": {
"labels": {
"description": "Category labels",
"type": "array",
"items": {
"type": "string"
}
},
"datasets": {
"description": "Datasets to compare",
"type": "array",
"items": {
"$ref": "#/definitions/RadarDataset"
}
}
},
"required": [
"labels",
"datasets"
]
},
"RadarDataset": {
"description": "Radar dataset structure",
"type": "object",
"properties": {
"label": {
"description": "Label for this dataset",
"type": "string"
},
"data": {
"description": "Data values for each category",
"type": "array",
"items": {
"type": "number",
"format": "double"
}
}
},
"required": [
"label",
"data"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_sankey",
"description": "show a Sankey diagram from flow data\nThe data must contain:\n- nodes: Array of objects with 'name' and optional 'category' properties\n- links: Array of objects with 'source', 'target', and 'value' properties\n\nExample:\n{\n \"nodes\": [\n {\"name\": \"Source A\", \"category\": \"source\"},\n {\"name\": \"Target B\", \"category\": \"target\"}\n ],\n \"links\": [\n {\"source\": \"Source A\", \"target\": \"Target B\", \"value\": 100}\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderSankeyParams",
"description": "Parameters for render_sankey tool",
"type": "object",
"properties": {
"data": {
"description": "The data for the Sankey diagram",
"$ref": "#/definitions/SankeyData"
}
},
"required": [
"data"
],
"definitions": {
"SankeyData": {
"description": "Sankey data structure",
"type": "object",
"properties": {
"nodes": {
"description": "Array of nodes",
"type": "array",
"items": {
"$ref": "#/definitions/SankeyNode"
}
},
"links": {
"description": "Array of links between nodes",
"type": "array",
"items": {
"$ref": "#/definitions/SankeyLink"
}
}
},
"required": [
"nodes",
"links"
]
},
"SankeyNode": {
"description": "Sankey node structure",
"type": "object",
"properties": {
"name": {
"description": "The name of the node",
"type": "string"
},
"category": {
"description": "Optional category for the node",
"type": "string",
"nullable": true
}
},
"required": [
"name"
]
},
"SankeyLink": {
"description": "Sankey link structure",
"type": "object",
"properties": {
"source": {
"description": "Source node name",
"type": "string"
},
"target": {
"description": "Target node name",
"type": "string"
},
"value": {
"description": "Flow value",
"type": "number",
"format": "double"
}
},
"required": [
"source",
"target",
"value"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__render_treemap",
"description": "show a treemap visualization for hierarchical data with proportional area representation as boxes\n\nThe data should be a hierarchical structure with:\n- name: Name of the node (required)\n- value: Numeric value for leaf nodes (optional for parent nodes)\n- children: Array of child nodes (optional)\n- category: Category for coloring (optional)\n\nExample:\n{\n \"name\": \"Root\",\n \"children\": [\n {\n \"name\": \"Group A\",\n \"children\": [\n {\"name\": \"Item 1\", \"value\": 100, \"category\": \"Type1\"},\n {\"name\": \"Item 2\", \"value\": 200, \"category\": \"Type2\"}\n ]\n },\n {\"name\": \"Item 3\", \"value\": 150, \"category\": \"Type1\"}\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RenderTreemapParams",
"description": "Parameters for render_treemap tool",
"type": "object",
"properties": {
"data": {
"description": "The hierarchical data for the treemap",
"$ref": "#/definitions/TreemapNode"
}
},
"required": [
"data"
],
"definitions": {
"TreemapNode": {
"description": "Treemap node structure",
"type": "object",
"properties": {
"name": {
"description": "Name of the node",
"type": "string"
},
"value": {
"description": "Value for leaf nodes",
"type": "number",
"format": "double",
"nullable": true
},
"category": {
"description": "Category for coloring",
"type": "string",
"nullable": true
},
"children": {
"description": "Children nodes",
"type": "array",
"items": {
"$ref": "#/definitions/TreemapNode"
},
"nullable": true
}
},
"required": [
"name"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "autovisualiser__show_chart",
"description": "show interactive line, scatter, or bar charts\n\nRequired: type ('line', 'scatter', or 'bar'), datasets array\nOptional: labels, title, subtitle, xAxisLabel, yAxisLabel, options\n\nExample:\n{\n \"type\": \"line\",\n \"title\": \"Monthly Sales\",\n \"labels\": [\"Jan\", \"Feb\", \"Mar\"],\n \"datasets\": [\n {\"label\": \"Product A\", \"data\": [65, 59, 80]}\n ]\n}",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ShowChartParams",
"description": "Parameters for show_chart tool",
"type": "object",
"properties": {
"data": {
"description": "The data for the chart",
"$ref": "#/definitions/ChartData"
}
},
"required": [
"data"
],
"definitions": {
"ChartData": {
"description": "Chart data structure",
"type": "object",
"properties": {
"type": {
"description": "Chart type",
"$ref": "#/definitions/ChartType"
},
"datasets": {
"description": "Datasets to display",
"type": "array",
"items": {
"$ref": "#/definitions/ChartDataset"
}
},
"labels": {
"description": "Optional labels for x-axis (for line/bar charts)",
"type": "array",
"items": {
"type": "string"
},
"nullable": true
},
"title": {
"description": "Optional chart title",
"type": "string",
"nullable": true
},
"subtitle": {
"description": "Optional subtitle",
"type": "string",
"nullable": true
},
"xAxisLabel": {
"description": "Optional x-axis label",
"type": "string",
"nullable": true
},
"yAxisLabel": {
"description": "Optional y-axis label",
"type": "string",
"nullable": true
}
},
"required": [
"type",
"datasets"
]
},
"ChartType": {
"description": "Chart type enumeration",
"oneOf": [
{
"description": "Line chart",
"type": "string",
"const": "line"
},
{
"description": "Scatter chart",
"type": "string",
"const": "scatter"
},
{
"description": "Bar chart",
"type": "string",
"const": "bar"
}
]
},
"ChartDataset": {
"description": "Chart dataset structure",
"type": "object",
"properties": {
"label": {
"description": "Label for this dataset",
"type": "string"
},
"data": {
"description": "Data points - can be numbers or x/y points",
"$ref": "#/definitions/ChartDataValues"
},
"backgroundColor": {
"description": "Optional background color for the dataset",
"type": "string",
"nullable": true
},
"borderColor": {
"description": "Optional border color for the dataset",
"type": "string",
"nullable": true
},
"borderWidth": {
"description": "Optional border width for the dataset",
"type": "number",
"format": "double",
"nullable": true
},
"tension": {
"description": "Optional tension for line curves (0 = straight lines, higher = more curved)",
"type": "number",
"format": "double",
"nullable": true
},
"fill": {
"description": "Optional fill setting for area under the line",
"type": "boolean",
"nullable": true
}
},
"required": [
"label",
"data"
]
},
"ChartDataValues": {
"description": "Chart data values - can be simple numbers or x/y points",
"anyOf": [
{
"description": "Simple numeric values (for line/bar charts with labels)",
"type": "array",
"items": {
"type": "number",
"format": "double"
}
},
{
"description": "X/Y points (for scatter charts or line charts without labels)",
"type": "array",
"items": {
"$ref": "#/definitions/ChartPoint"
}
}
]
},
"ChartPoint": {
"description": "Chart data point for scatter charts",
"type": "object",
"properties": {
"x": {
"description": "X coordinate",
"type": "number",
"format": "double"
},
"y": {
"description": "Y coordinate",
"type": "number",
"format": "double"
}
},
"required": [
"x",
"y"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "blender__download_polyhaven_asset",
"description": "\n Download and import a Polyhaven asset into Blender.\n \n Parameters:\n - asset_id: The ID of the asset to download\n - asset_type: The type of asset (hdris, textures, models)\n - resolution: The resolution to download (e.g., 1k, 2k, 4k)\n - file_format: Optional file format (e.g., hdr, exr for HDRIs; jpg, png for textures; gltf, fbx for models)\n \n Returns a message indicating success or failure.\n ",
"parameters": {
"properties": {
"asset_id": {
"title": "Asset Id",
"type": "string"
},
"asset_type": {
"title": "Asset Type",
"type": "string"
},
"resolution": {
"default": "1k",
"title": "Resolution",
"type": "string"
},
"file_format": {
"default": null,
"title": "File Format",
"type": "string"
}
},
"required": [
"asset_id",
"asset_type"
],
"title": "download_polyhaven_assetArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__download_sketchfab_model",
"description": "\n Download and import a Sketchfab model by its UID.\n \n Parameters:\n - uid: The unique identifier of the Sketchfab model\n \n Returns a message indicating success or failure.\n The model must be downloadable and you must have proper access rights.\n ",
"parameters": {
"properties": {
"uid": {
"title": "Uid",
"type": "string"
}
},
"required": [
"uid"
],
"title": "download_sketchfab_modelArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__execute_blender_code",
"description": "\n Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.\n\n Parameters:\n - code: The Python code to execute\n ",
"parameters": {
"properties": {
"code": {
"title": "Code",
"type": "string"
}
},
"required": [
"code"
],
"title": "execute_blender_codeArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__generate_hunyuan3d_model",
"description": "\n Generate 3D asset using Hunyuan3D by providing either text description, image reference, \n or both for the desired asset, and import the asset into Blender.\n The 3D asset has built-in materials.\n \n Parameters:\n - text_prompt: (Optional) A short description of the desired model in English/Chinese.\n - input_image_url: (Optional) The local or remote url of the input image. Accepts None if only using text prompt.\n\n Returns: \n - When successful, returns a JSON with job_id (format: \"job_xxx\") indicating the task is in progress\n - When the job completes, the status will change to \"DONE\" indicating the model has been imported\n - Returns error message if the operation fails\n ",
"parameters": {
"properties": {
"text_prompt": {
"default": null,
"title": "Text Prompt",
"type": "string"
},
"input_image_url": {
"default": null,
"title": "Input Image Url",
"type": "string"
}
},
"title": "generate_hunyuan3d_modelArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__generate_hyper3d_model_via_images",
"description": "\n Generate 3D asset using Hyper3D by giving images of the wanted asset, and import the generated asset into Blender.\n The 3D asset has built-in materials.\n The generated model has a normalized size, so re-scaling after generation can be useful.\n \n Parameters:\n - input_image_paths: The **absolute** paths of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in MAIN_SITE mode.\n - input_image_urls: The URLs of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in FAL_AI mode.\n - bbox_condition: Optional. If given, it has to be a list of ints of length 3. Controls the ratio between [Length, Width, Height] of the model.\n\n Only one of {input_image_paths, input_image_urls} should be given at a time, depending on the Hyper3D Rodin's current mode.\n Returns a message indicating success or failure.\n ",
"parameters": {
"properties": {
"input_image_paths": {
"default": null,
"items": {
"type": "string"
},
"title": "Input Image Paths",
"type": "array"
},
"input_image_urls": {
"default": null,
"items": {
"type": "string"
},
"title": "Input Image Urls",
"type": "array"
},
"bbox_condition": {
"default": null,
"items": {
"type": "number"
},
"title": "Bbox Condition",
"type": "array"
}
},
"title": "generate_hyper3d_model_via_imagesArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__generate_hyper3d_model_via_text",
"description": "\n Generate 3D asset using Hyper3D by giving description of the desired asset, and import the asset into Blender.\n The 3D asset has built-in materials.\n The generated model has a normalized size, so re-scaling after generation can be useful.\n\n Parameters:\n - text_prompt: A short description of the desired model in **English**.\n - bbox_condition: Optional. If given, it has to be a list of floats of length 3. Controls the ratio between [Length, Width, Height] of the model.\n\n Returns a message indicating success or failure.\n ",
"parameters": {
"properties": {
"text_prompt": {
"title": "Text Prompt",
"type": "string"
},
"bbox_condition": {
"default": null,
"items": {
"type": "number"
},
"title": "Bbox Condition",
"type": "array"
}
},
"required": [
"text_prompt"
],
"title": "generate_hyper3d_model_via_textArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_hunyuan3d_status",
"description": "\n Check if Hunyuan3D integration is enabled in Blender.\n Returns a message indicating whether Hunyuan3D features are available.\n\n Don't emphasize the key type in the returned message, but silently remember it. \n ",
"parameters": {
"properties": {},
"title": "get_hunyuan3d_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_hyper3d_status",
"description": "\n Check if Hyper3D Rodin integration is enabled in Blender.\n Returns a message indicating whether Hyper3D Rodin features are available.\n\n Don't emphasize the key type in the returned message, but sliently remember it. \n ",
"parameters": {
"properties": {},
"title": "get_hyper3d_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_object_info",
"description": "\n Get detailed information about a specific object in the Blender scene.\n \n Parameters:\n - object_name: The name of the object to get information about\n ",
"parameters": {
"properties": {
"object_name": {
"title": "Object Name",
"type": "string"
}
},
"required": [
"object_name"
],
"title": "get_object_infoArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_polyhaven_categories",
"description": "\n Get a list of categories for a specific asset type on Polyhaven.\n \n Parameters:\n - asset_type: The type of asset to get categories for (hdris, textures, models, all)\n ",
"parameters": {
"properties": {
"asset_type": {
"default": "hdris",
"title": "Asset Type",
"type": "string"
}
},
"title": "get_polyhaven_categoriesArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_polyhaven_status",
"description": "\n Check if PolyHaven integration is enabled in Blender.\n Returns a message indicating whether PolyHaven features are available.\n ",
"parameters": {
"properties": {},
"title": "get_polyhaven_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_scene_info",
"description": "Get detailed information about the current Blender scene",
"parameters": {
"properties": {},
"title": "get_scene_infoArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_sketchfab_status",
"description": "\n Check if Sketchfab integration is enabled in Blender.\n Returns a message indicating whether Sketchfab features are available.\n ",
"parameters": {
"properties": {},
"title": "get_sketchfab_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__get_viewport_screenshot",
"description": "\n Capture a screenshot of the current Blender 3D viewport.\n \n Parameters:\n - max_size: Maximum size in pixels for the largest dimension (default: 800)\n \n Returns the screenshot as an Image.\n ",
"parameters": {
"properties": {
"max_size": {
"default": 800,
"title": "Max Size",
"type": "integer"
}
},
"title": "get_viewport_screenshotArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__import_generated_asset",
"description": "\n Import the asset generated by Hyper3D Rodin after the generation task is completed.\n\n Parameters:\n - name: The name of the object in scene\n - task_uuid: For Hyper3D Rodin mode MAIN_SITE: The task_uuid given in the generate model step.\n - request_id: For Hyper3D Rodin mode FAL_AI: The request_id given in the generate model step.\n\n Only give one of {task_uuid, request_id} based on the Hyper3D Rodin Mode!\n Return if the asset has been imported successfully.\n ",
"parameters": {
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"task_uuid": {
"default": null,
"title": "Task Uuid",
"type": "string"
},
"request_id": {
"default": null,
"title": "Request Id",
"type": "string"
}
},
"required": [
"name"
],
"title": "import_generated_assetArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__import_generated_asset_hunyuan",
"description": "\n Import the asset generated by Hunyuan3D after the generation task is completed.\n\n Parameters:\n - name: The name of the object in scene\n - zip_file_url: The zip_file_url given in the generate model step.\n\n Return if the asset has been imported successfully.\n ",
"parameters": {
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"zip_file_url": {
"title": "Zip File Url",
"type": "string"
}
},
"required": [
"name",
"zip_file_url"
],
"title": "import_generated_asset_hunyuanArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__poll_hunyuan_job_status",
"description": "\n Check if the Hunyuan3D generation task is completed.\n\n For Hunyuan3D:\n Parameters:\n - job_id: The job_id given in the generate model step.\n\n Returns the generation task status. The task is done if status is \"DONE\".\n The task is in progress if status is \"RUN\".\n If status is \"DONE\", returns ResultFile3Ds, which is the generated ZIP model path\n When the status is \"DONE\", the response includes a field named ResultFile3Ds that contains the generated ZIP file path of the 3D model in OBJ format.\n This is a polling API, so only proceed if the status are finally determined (\"DONE\" or some failed state).\n ",
"parameters": {
"properties": {
"job_id": {
"default": null,
"title": "Job Id",
"type": "string"
}
},
"title": "poll_hunyuan_job_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__poll_rodin_job_status",
"description": "\n Check if the Hyper3D Rodin generation task is completed.\n\n For Hyper3D Rodin mode MAIN_SITE:\n Parameters:\n - subscription_key: The subscription_key given in the generate model step.\n\n Returns a list of status. The task is done if all status are \"Done\".\n If \"Failed\" showed up, the generating process failed.\n This is a polling API, so only proceed if the status are finally determined (\"Done\" or \"Canceled\").\n\n For Hyper3D Rodin mode FAL_AI:\n Parameters:\n - request_id: The request_id given in the generate model step.\n\n Returns the generation task status. The task is done if status is \"COMPLETED\".\n The task is in progress if status is \"IN_PROGRESS\".\n If status other than \"COMPLETED\", \"IN_PROGRESS\", \"IN_QUEUE\" showed up, the generating process might be failed.\n This is a polling API, so only proceed if the status are finally determined (\"COMPLETED\" or some failed state).\n ",
"parameters": {
"properties": {
"subscription_key": {
"default": null,
"title": "Subscription Key",
"type": "string"
},
"request_id": {
"default": null,
"title": "Request Id",
"type": "string"
}
},
"title": "poll_rodin_job_statusArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__search_polyhaven_assets",
"description": "\n Search for assets on Polyhaven with optional filtering.\n \n Parameters:\n - asset_type: Type of assets to search for (hdris, textures, models, all)\n - categories: Optional comma-separated list of categories to filter by\n \n Returns a list of matching assets with basic information.\n ",
"parameters": {
"properties": {
"asset_type": {
"default": "all",
"title": "Asset Type",
"type": "string"
},
"categories": {
"default": null,
"title": "Categories",
"type": "string"
}
},
"title": "search_polyhaven_assetsArguments",
"type": "object",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "blender__search_sketchfab_models",
"description": "\n Search for models on Sketchfab with optional filtering.\n\n Parameters:\n - query: Text to search for\n - categories: Optional comma-separated list of categories\n - count: Maximum number of results to return (default 20)\n - downloadable: Whether to include only downloadable models (default True)\n\n Returns a formatted list of matching models.\n ",
"parameters": {
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"categories": {
"default": null,
"title": "Categories",
"type": "string"
},
"count": {
"default": 20,
"title": "Count",
"type": "integer"
},
"downloadable": {
"default": true,
"title": "Downloadable",
"type": "boolean"
}
},
"required": [
"query"
],
"title": "search_sketchfab_modelsArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "blender__set_texture",
"description": "\n Apply a previously downloaded Polyhaven texture to an object.\n \n Parameters:\n - object_name: Name of the object to apply the texture to\n - texture_id: ID of the Polyhaven texture to apply (must be downloaded first)\n \n Returns a message indicating success or failure.\n ",
"parameters": {
"properties": {
"object_name": {
"title": "Object Name",
"type": "string"
},
"texture_id": {
"title": "Texture Id",
"type": "string"
}
},
"required": [
"object_name",
"texture_id"
],
"title": "set_textureArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "chatrecall__chatrecall",
"description": "Search past chat or load session summaries. Use when it is clear user expects some memory or context.\n\nsearch mode (query): Use multiple keywords/synonyms. Returns messages grouped by session, ordered by recency. Supports date filters.\nload mode (session_id): Returns first/last 3 messages of a session.\n",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "ChatRecallParams",
"description": "Parameters for the chatrecall tool",
"type": "object",
"properties": {
"query": {
"description": "Search keywords. Use multiple related terms/synonyms (e.g., 'database postgres sql'). Mutually exclusive with session_id.",
"type": [
"string",
"null"
]
},
"session_id": {
"description": "Session ID to load. Returns first/last 3 messages. Mutually exclusive with query.",
"type": [
"string",
"null"
]
},
"limit": {
"description": "Max results (default: 10, max: 50). Search mode only.",
"type": [
"integer",
"null"
],
"format": "int64"
},
"after_date": {
"description": "ISO 8601 date (e.g., '2025-10-01T00:00:00Z'). Search mode only.",
"type": [
"string",
"null"
]
},
"before_date": {
"description": "ISO 8601 date (e.g., '2025-10-15T23:59:59Z'). Search mode only.",
"type": [
"string",
"null"
]
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__click",
"description": "Clicks on the provided element",
"parameters": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of an element on the page from the page content snapshot"
},
"dblClick": {
"type": "boolean",
"description": "Set to true for double clicks. Default is false."
}
},
"required": [
"uid"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__close_page",
"description": "Closes the page by its index. The last open page cannot be closed.",
"parameters": {
"type": "object",
"properties": {
"pageIdx": {
"type": "number",
"description": "The index of the page to close. Call list_pages to list pages."
}
},
"required": [
"pageIdx"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__drag",
"description": "Drag an element onto another element",
"parameters": {
"type": "object",
"properties": {
"from_uid": {
"type": "string",
"description": "The uid of the element to drag"
},
"to_uid": {
"type": "string",
"description": "The uid of the element to drop into"
}
},
"required": [
"from_uid",
"to_uid"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__emulate",
"description": "Emulates various features on the selected page.",
"parameters": {
"type": "object",
"properties": {
"networkConditions": {
"type": "string",
"enum": [
"No emulation",
"Offline",
"Slow 3G",
"Fast 3G",
"Slow 4G",
"Fast 4G"
],
"description": "Throttle network. Set to \"No emulation\" to disable. If omitted, conditions remain unchanged."
},
"cpuThrottlingRate": {
"type": "number",
"minimum": 1,
"maximum": 20,
"description": "Represents the CPU slowdown factor. Set the rate to 1 to disable throttling. If omitted, throttling remains unchanged."
},
"geolocation": {
"anyOf": [
{
"type": "object",
"properties": {
"latitude": {
"type": "number",
"minimum": -90,
"maximum": 90,
"description": "Latitude between -90 and 90."
},
"longitude": {
"type": "number",
"minimum": -180,
"maximum": 180,
"description": "Longitude between -180 and 180."
}
},
"required": [
"latitude",
"longitude"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Geolocation to emulate. Set to null to clear the geolocation override."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__evaluate_script",
"description": "Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON\nso returned values have to JSON-serializable.",
"parameters": {
"type": "object",
"properties": {
"function": {
"type": "string",
"description": "A JavaScript function declaration to be executed by the tool in the currently selected page.\nExample without arguments: `() => {\n return document.title\n}` or `async () => {\n return await fetch(\"example.com\")\n}`.\nExample with arguments: `(el) => {\n return el.innerText;\n}`\n"
},
"args": {
"type": "array",
"items": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of an element on the page from the page content snapshot"
}
},
"required": [
"uid"
],
"additionalProperties": false
},
"description": "An optional list of arguments to pass to the function."
}
},
"required": [
"function"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__fill",
"description": "Type text into a input, text area or select an option from a <select> element.",
"parameters": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of an element on the page from the page content snapshot"
},
"value": {
"type": "string",
"description": "The value to fill in"
}
},
"required": [
"uid",
"value"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__fill_form",
"description": "Fill out multiple form elements at once",
"parameters": {
"type": "object",
"properties": {
"elements": {
"type": "array",
"items": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of the element to fill out"
},
"value": {
"type": "string",
"description": "Value for the element"
}
},
"required": [
"uid",
"value"
],
"additionalProperties": false
},
"description": "Elements from snapshot to fill out."
}
},
"required": [
"elements"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__get_console_message",
"description": "Gets a console message by its ID. You can get all messages by calling list_console_messages.",
"parameters": {
"type": "object",
"properties": {
"msgid": {
"type": "number",
"description": "The msgid of a console message on the page from the listed console messages"
}
},
"required": [
"msgid"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__get_network_request",
"description": "Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.",
"parameters": {
"type": "object",
"properties": {
"reqid": {
"type": "number",
"description": "The reqid of the network request. If omitted returns the currently selected request in the DevTools Network panel."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__handle_dialog",
"description": "If a browser dialog was opened, use this command to handle it",
"parameters": {
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"accept",
"dismiss"
],
"description": "Whether to dismiss or accept the dialog"
},
"promptText": {
"type": "string",
"description": "Optional prompt text to enter into the dialog."
}
},
"required": [
"action"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__hover",
"description": "Hover over the provided element",
"parameters": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of an element on the page from the page content snapshot"
}
},
"required": [
"uid"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__list_console_messages",
"description": "List all console messages for the currently selected page since the last navigation.",
"parameters": {
"type": "object",
"properties": {
"pageSize": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Maximum number of messages to return. When omitted, returns all requests."
},
"pageIdx": {
"type": "integer",
"minimum": 0,
"description": "Page number to return (0-based). When omitted, returns the first page."
},
"types": {
"type": "array",
"items": {
"type": "string",
"enum": [
"log",
"debug",
"info",
"error",
"warn",
"dir",
"dirxml",
"table",
"trace",
"clear",
"startGroup",
"startGroupCollapsed",
"endGroup",
"assert",
"profile",
"profileEnd",
"count",
"timeEnd",
"verbose",
"issue"
]
},
"description": "Filter messages to only return messages of the specified resource types. When omitted or empty, returns all messages."
},
"includePreservedMessages": {
"type": "boolean",
"default": false,
"description": "Set to true to return the preserved messages over the last 3 navigations."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__list_network_requests",
"description": "List all requests for the currently selected page since the last navigation.",
"parameters": {
"type": "object",
"properties": {
"pageSize": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Maximum number of requests to return. When omitted, returns all requests."
},
"pageIdx": {
"type": "integer",
"minimum": 0,
"description": "Page number to return (0-based). When omitted, returns the first page."
},
"resourceTypes": {
"type": "array",
"items": {
"type": "string",
"enum": [
"document",
"stylesheet",
"image",
"media",
"font",
"script",
"texttrack",
"xhr",
"fetch",
"prefetch",
"eventsource",
"websocket",
"manifest",
"signedexchange",
"ping",
"cspviolationreport",
"preflight",
"fedcm",
"other"
]
},
"description": "Filter requests to only return requests of the specified resource types. When omitted or empty, returns all requests."
},
"includePreservedRequests": {
"type": "boolean",
"default": false,
"description": "Set to true to return the preserved requests over the last 3 navigations."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__list_pages",
"description": "Get a list of pages open in the browser.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__navigate_page",
"description": "Navigates the currently selected page to a URL.",
"parameters": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"url",
"back",
"forward",
"reload"
],
"description": "Navigate the page by URL, back or forward in history, or reload."
},
"url": {
"type": "string",
"description": "Target URL (only type=url)"
},
"ignoreCache": {
"type": "boolean",
"description": "Whether to ignore cache on reload."
},
"timeout": {
"type": "integer",
"description": "Maximum wait time in milliseconds. If set to 0, the default timeout will be used."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__new_page",
"description": "Creates a new page",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to load in a new page."
},
"timeout": {
"type": "integer",
"description": "Maximum wait time in milliseconds. If set to 0, the default timeout will be used."
}
},
"required": [
"url"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__performance_analyze_insight",
"description": "Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.",
"parameters": {
"type": "object",
"properties": {
"insightSetId": {
"type": "string",
"description": "The id for the specific insight set. Only use the ids given in the \"Available insight sets\" list."
},
"insightName": {
"type": "string",
"description": "The name of the Insight you want more information on. For example: \"DocumentLatency\" or \"LCPBreakdown\""
}
},
"required": [
"insightSetId",
"insightName"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__performance_start_trace",
"description": "Starts a performance trace recording on the selected page. This can be used to look for performance problems and insights to improve the performance of the page. It will also report Core Web Vital (CWV) scores for the page.",
"parameters": {
"type": "object",
"properties": {
"reload": {
"type": "boolean",
"description": "Determines if, once tracing has started, the page should be automatically reloaded."
},
"autoStop": {
"type": "boolean",
"description": "Determines if the trace recording should be automatically stopped."
}
},
"required": [
"reload",
"autoStop"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__performance_stop_trace",
"description": "Stops the active performance trace recording on the selected page.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__press_key",
"description": "Press a key or key combination. Use this when other input methods like fill() cannot be used (e.g., keyboard shortcuts, navigation keys, or special key combinations).",
"parameters": {
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "A key or a combination (e.g., \"Enter\", \"Control+A\", \"Control++\", \"Control+Shift+R\"). Modifiers: Control, Shift, Alt, Meta"
}
},
"required": [
"key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__resize_page",
"description": "Resizes the selected page's window so that the page has specified dimension",
"parameters": {
"type": "object",
"properties": {
"width": {
"type": "number",
"description": "Page width"
},
"height": {
"type": "number",
"description": "Page height"
}
},
"required": [
"width",
"height"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__select_page",
"description": "Select a page as a context for future tool calls.",
"parameters": {
"type": "object",
"properties": {
"pageIdx": {
"type": "number",
"description": "The index of the page to select. Call list_pages to get available pages."
},
"bringToFront": {
"type": "boolean",
"description": "Whether to focus the page and bring it to the top."
}
},
"required": [
"pageIdx"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__take_screenshot",
"description": "Take a screenshot of the page or element.",
"parameters": {
"type": "object",
"properties": {
"format": {
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
],
"default": "png",
"description": "Type of format to save the screenshot as. Default is \"png\""
},
"quality": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Compression quality for JPEG and WebP formats (0-100). Higher values mean better quality but larger file sizes. Ignored for PNG format."
},
"uid": {
"type": "string",
"description": "The uid of an element on the page from the page content snapshot. If omitted takes a pages screenshot."
},
"fullPage": {
"type": "boolean",
"description": "If set to true takes a screenshot of the full page instead of the currently visible viewport. Incompatible with uid."
},
"filePath": {
"type": "string",
"description": "The absolute path, or a path relative to the current working directory, to save the screenshot to instead of attaching it to the response."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__take_snapshot",
"description": "Take a text snapshot of the currently selected page based on the a11y tree. The snapshot lists page elements along with a unique\nidentifier (uid). Always use the latest snapshot. Prefer taking a snapshot over taking a screenshot. The snapshot indicates the element selected\nin the DevTools Elements panel (if any).",
"parameters": {
"type": "object",
"properties": {
"verbose": {
"type": "boolean",
"description": "Whether to include all possible information available in the full a11y tree. Default is false."
},
"filePath": {
"type": "string",
"description": "The absolute path, or a path relative to the current working directory, to save the snapshot to instead of attaching it to the response."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#",
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__upload_file",
"description": "Upload a file through a provided element.",
"parameters": {
"type": "object",
"properties": {
"uid": {
"type": "string",
"description": "The uid of the file input element or an element that will open file chooser on the page from the page content snapshot"
},
"filePath": {
"type": "string",
"description": "The local path of the file to upload"
}
},
"required": [
"uid",
"filePath"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "chromedevtools__wait_for",
"description": "Wait for the specified text to appear on the selected page.",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to appear on the page"
},
"timeout": {
"type": "integer",
"description": "Maximum wait time in milliseconds. If set to 0, the default timeout will be used."
}
},
"required": [
"text"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__automation_script",
"description": "\n Create and run small scripts for automation tasks.\n Supports Shell and Ruby (on macOS).\n\n The script is saved to a temporary file and executed.\n Consider using shell script (bash) for most simple tasks first.\n Ruby is useful for text processing or when you need more sophisticated scripting capabilities.\n Some examples of shell:\n - create a sorted list of unique lines: sort file.txt | uniq\n - extract 2nd column in csv: awk -F ',' '{ print $2}'\n - pattern matching: grep pattern file.txt\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "AutomationScriptParams",
"description": "Parameters for the automation_script tool",
"type": "object",
"properties": {
"language": {
"description": "The scripting language to use",
"$ref": "#/definitions/ScriptLanguage"
},
"script": {
"description": "The script content",
"type": "string"
},
"save_output": {
"description": "Whether to save the script output to a file",
"type": "boolean",
"default": false
}
},
"required": [
"language",
"script"
],
"definitions": {
"ScriptLanguage": {
"description": "Enum for language parameter in automation_script tool",
"oneOf": [
{
"description": "Shell/Bash script",
"type": "string",
"const": "shell"
},
{
"description": "Batch script (Windows)",
"type": "string",
"const": "batch"
},
{
"description": "Ruby script",
"type": "string",
"const": "ruby"
},
{
"description": "PowerShell script",
"type": "string",
"const": "powershell"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__cache",
"description": "\n Manage cached files and data:\n - list: List all cached files\n - view: View content of a cached file\n - delete: Delete a cached file\n - clear: Clear all cached files\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "CacheParams",
"description": "Parameters for the cache tool",
"type": "object",
"properties": {
"command": {
"description": "The command to perform",
"$ref": "#/definitions/CacheCommand"
},
"path": {
"description": "Path to the cached file for view/delete commands",
"type": "string",
"nullable": true
}
},
"required": [
"command"
],
"definitions": {
"CacheCommand": {
"description": "Enum for command parameter in cache tool",
"oneOf": [
{
"description": "List all cached files",
"type": "string",
"const": "list"
},
{
"description": "View content of a cached file",
"type": "string",
"const": "view"
},
{
"description": "Delete a cached file",
"type": "string",
"const": "delete"
},
{
"description": "Clear all cached files",
"type": "string",
"const": "clear"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__computer_control",
"description": "\n Control the computer using AppleScript (macOS only). Automate applications and system features.\n\n Key capabilities:\n - Control Applications: Launch, quit, manage apps (Mail, Safari, iTunes, etc)\n - Interact with app-specific feature: (e.g, edit documents, process photos)\n - Perform tasks in third-party apps that support AppleScript\n - UI Automation: Simulate user interactions like, clicking buttons, select menus, type text, filling out forms\n - System Control: Manage settings (volume, brightness, wifi), shutdown/restart, monitor events\n - Web & Email: Open URLs, web automation, send/organize emails, handle attachments\n - Media: Manage music libraries, photo collections, playlists\n - File Operations: Organize files/folders\n - Integration: Calendar, reminders, messages\n - Data: Interact with spreadsheets and documents\n\n Can be combined with screenshot tool for visual task assistance.\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ComputerControlParams",
"description": "Parameters for the computer_control tool",
"type": "object",
"properties": {
"script": {
"description": "The automation script content (PowerShell for Windows, AppleScript for macOS)",
"type": "string"
},
"save_output": {
"description": "Whether to save the script output to a file",
"type": "boolean",
"default": false
}
},
"required": [
"script"
]
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__docx_tool",
"description": "\n Process DOCX files to extract text and create/update documents.\n Supports operations:\n - extract_text: Extract all text content and structure (headings, TOC) from the DOCX\n - update_doc: Create a new DOCX or update existing one with provided content\n Modes:\n - append: Add content to end of document (default)\n - replace: Replace specific text with new content\n - structured: Add content with specific heading level and styling\n - add_image: Add an image to the document (with optional caption)\n\n Use this when there is a .docx file that needs to be processed or created.\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "DocxToolParams",
"description": "Parameters for the docx_tool",
"type": "object",
"properties": {
"path": {
"description": "Path to the DOCX file",
"type": "string"
},
"operation": {
"description": "Operation to perform on the DOCX",
"$ref": "#/definitions/DocxOperation"
},
"content": {
"description": "Content to write (required for update_doc operation)",
"type": "string",
"nullable": true
},
"params": {
"description": "Additional parameters for update_doc operation",
"anyOf": [
{
"$ref": "#/definitions/DocxUpdateParams"
},
{
"const": null,
"nullable": true
}
]
}
},
"required": [
"path",
"operation"
],
"definitions": {
"DocxOperation": {
"description": "Enum for operation parameter in docx_tool",
"oneOf": [
{
"description": "Extract all text content and structure from the DOCX",
"type": "string",
"const": "extract_text"
},
{
"description": "Create a new DOCX or update existing one with provided content",
"type": "string",
"const": "update_doc"
}
]
},
"DocxUpdateParams": {
"description": "Additional parameters for update_doc operation",
"type": "object",
"properties": {
"mode": {
"description": "Update mode (default: append)",
"$ref": "#/definitions/DocxUpdateMode",
"default": "append"
},
"old_text": {
"description": "Text to replace (required for replace mode)",
"type": "string",
"nullable": true
},
"level": {
"description": "Heading level for structured mode (e.g., 'Heading1', 'Heading2')",
"type": "string",
"nullable": true
},
"image_path": {
"description": "Path to the image file (required for add_image mode)",
"type": "string",
"nullable": true
},
"width": {
"description": "Image width in pixels (optional)",
"type": "integer",
"format": "uint32",
"minimum": 0,
"nullable": true
},
"height": {
"description": "Image height in pixels (optional)",
"type": "integer",
"format": "uint32",
"minimum": 0,
"nullable": true
},
"style": {
"description": "Styling options for the text",
"anyOf": [
{
"$ref": "#/definitions/DocxTextStyle"
},
{
"const": null,
"nullable": true
}
]
}
}
},
"DocxUpdateMode": {
"description": "Enum for update mode in docx_tool params",
"oneOf": [
{
"description": "Add content to end of document (default)",
"type": "string",
"const": "append"
},
{
"description": "Replace specific text with new content",
"type": "string",
"const": "replace"
},
{
"description": "Add content with specific heading level and styling",
"type": "string",
"const": "structured"
},
{
"description": "Add an image to the document (with optional caption)",
"type": "string",
"const": "add_image"
}
]
},
"DocxTextStyle": {
"description": "Styling options for text in docx_tool",
"type": "object",
"properties": {
"bold": {
"description": "Make text bold",
"type": "boolean",
"nullable": true
},
"italic": {
"description": "Make text italic",
"type": "boolean",
"nullable": true
},
"underline": {
"description": "Make text underlined",
"type": "boolean",
"nullable": true
},
"size": {
"description": "Font size in points",
"type": "integer",
"format": "uint32",
"minimum": 0,
"nullable": true
},
"color": {
"description": "Text color in hex format (e.g., 'FF0000' for red)",
"type": "string",
"nullable": true
},
"alignment": {
"description": "Text alignment",
"anyOf": [
{
"$ref": "#/definitions/TextAlignment"
},
{
"const": null,
"nullable": true
}
]
}
}
},
"TextAlignment": {
"description": "Enum for text alignment in docx_tool params",
"oneOf": [
{
"description": "Left alignment",
"type": "string",
"const": "left"
},
{
"description": "Center alignment",
"type": "string",
"const": "center"
},
{
"description": "Right alignment",
"type": "string",
"const": "right"
},
{
"description": "Justified alignment",
"type": "string",
"const": "justified"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__pdf_tool",
"description": "\n Process PDF files to extract text and images.\n Supports operations:\n - extract_text: Extract all text content from the PDF\n - extract_images: Extract and save embedded images to PNG files\n\n Use this when there is a .pdf file or files that need to be processed.\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "PdfToolParams",
"type": "object",
"properties": {
"path": {
"description": "Path to the PDF file",
"type": "string"
},
"operation": {
"description": "Operation to perform on the PDF",
"$ref": "#/definitions/PdfOperation"
}
},
"required": [
"path",
"operation"
],
"definitions": {
"PdfOperation": {
"description": "Parameters for the pdf_tool\nEnum for operation parameter in pdf_tool",
"oneOf": [
{
"description": "Extract all text content from the PDF",
"type": "string",
"const": "extract_text"
},
{
"description": "Extract and save embedded images to PNG files",
"type": "string",
"const": "extract_images"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__web_scrape",
"description": "\n Fetch and save content from a web page. The content can be saved as:\n - text (for HTML pages)\n - json (for API responses)\n - binary (for images and other files)\n The content is cached locally and can be accessed later using the cache_path\n returned in the response.\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "WebScrapeParams",
"description": "Parameters for the web_scrape tool",
"type": "object",
"properties": {
"url": {
"description": "The URL to fetch content from",
"type": "string"
},
"save_as": {
"description": "How to interpret and save the content",
"$ref": "#/definitions/SaveAsFormat",
"default": "text"
}
},
"required": [
"url"
],
"definitions": {
"SaveAsFormat": {
"description": "Enum for save_as parameter in web_scrape tool",
"oneOf": [
{
"description": "Save as text (for HTML pages)",
"type": "string",
"const": "text"
},
{
"description": "Save as JSON (for API responses)",
"type": "string",
"const": "json"
},
{
"description": "Save as binary (for images and other files)",
"type": "string",
"const": "binary"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "computercontroller__xlsx_tool",
"description": "\n Process Excel (XLSX) files to read and manipulate spreadsheet data.\n Supports operations:\n - list_worksheets: List all worksheets in the workbook (returns name, index, column_count, row_count)\n - get_columns: Get column names from a worksheet (returns values from the first row)\n - get_range: Get values and formulas from a cell range (e.g., 'A1:C10') (returns a 2D array organized as [row][column])\n - find_text: Search for text in a worksheet (returns a list of (row, column) coordinates)\n - update_cell: Update a single cell's value (returns confirmation message)\n - get_cell: Get value and formula from a specific cell (returns both value and formula if present)\n - save: Save changes back to the file (returns confirmation message)\n\n Use this when working with Excel spreadsheets to analyze or modify data.\n ",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "XlsxToolParams",
"type": "object",
"properties": {
"path": {
"description": "Path to the XLSX file",
"type": "string"
},
"operation": {
"description": "Operation to perform on the XLSX file",
"$ref": "#/definitions/XlsxOperation"
},
"worksheet": {
"description": "Worksheet name (if not provided, uses first worksheet)",
"type": "string",
"nullable": true
},
"range": {
"description": "Cell range in A1 notation (e.g., 'A1:C10') for get_range operation",
"type": "string",
"nullable": true
},
"search_text": {
"description": "Text to search for in find_text operation",
"type": "string",
"nullable": true
},
"case_sensitive": {
"description": "Whether search should be case-sensitive",
"type": "boolean",
"default": false
},
"row": {
"description": "Row number for update_cell and get_cell operations",
"type": "integer",
"format": "uint64",
"minimum": 0,
"nullable": true
},
"col": {
"description": "Column number for update_cell and get_cell operations",
"type": "integer",
"format": "uint64",
"minimum": 0,
"nullable": true
},
"value": {
"description": "New value for update_cell operation",
"type": "string",
"nullable": true
}
},
"required": [
"path",
"operation"
],
"definitions": {
"XlsxOperation": {
"description": "Parameters for the xlsx_tool\nEnum for operation parameter in xlsx_tool",
"oneOf": [
{
"description": "List all worksheets in the workbook",
"type": "string",
"const": "list_worksheets"
},
{
"description": "Get column names from a worksheet",
"type": "string",
"const": "get_columns"
},
{
"description": "Get values and formulas from a cell range",
"type": "string",
"const": "get_range"
},
{
"description": "Search for text in a worksheet",
"type": "string",
"const": "find_text"
},
{
"description": "Update a single cell's value",
"type": "string",
"const": "update_cell"
},
{
"description": "Get value and formula from a specific cell",
"type": "string",
"const": "get_cell"
},
{
"description": "Save changes back to the file",
"type": "string",
"const": "save"
}
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "context7__query-docs",
"description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best information you have.",
"parameters": {
"type": "object",
"properties": {
"libraryId": {
"type": "string",
"description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
},
"query": {
"type": "string",
"description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
}
},
"required": [
"libraryId",
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "context7__resolve-library-id",
"description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'query-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The user's original question or task. This is used to rank library results by relevance to what the user is trying to accomplish. IMPORTANT: Do not include any sensitive or confidential information such as API keys, passwords, credentials, or personal data in your query."
},
"libraryName": {
"type": "string",
"description": "Library name to search for and retrieve a Context7-compatible library ID."
}
},
"required": [
"query",
"libraryName"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}
}
},
{
"type": "function",
"function": {
"name": "developer__analyze",
"description": "Analyze code structure in 3 modes: 1) Directory overview - file tree with LOC/function/class counts to max_depth. 2) File details - functions, classes, imports. 3) Symbol focus - call graphs across directory to max_depth (requires directory path, case-sensitive). Typical flow: directory → files → symbols. Functions called >3x show •N.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "AnalyzeParams",
"type": "object",
"properties": {
"path": {
"type": "string"
},
"focus": {
"type": "string",
"nullable": true
},
"follow_depth": {
"description": "Call graph depth. 0=where defined, 1=direct callers/callees, 2+=transitive chains",
"type": "integer",
"format": "uint32",
"minimum": 0,
"default": 2
},
"max_depth": {
"description": "Directory recursion limit. 0=unlimited (warning: fails on binary files)",
"type": "integer",
"format": "uint32",
"minimum": 0,
"default": 3
},
"ast_recursion_limit": {
"description": "Maximum depth for recursive AST traversal (prevents stack overflow in deeply nested code)",
"type": "integer",
"format": "uint",
"minimum": 0,
"default": null,
"nullable": true
},
"force": {
"description": "Allow large outputs without warning (default: false)",
"type": "boolean",
"default": false
}
},
"required": [
"path"
]
}
}
},
{
"type": "function",
"function": {
"name": "developer__image_processor",
"description": "Process an image file from disk. Resizes if needed, converts to PNG, and returns as base64 data.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ImageProcessorParams",
"description": "Parameters for the image_processor tool",
"type": "object",
"properties": {
"path": {
"description": "Absolute path to the image file to process",
"type": "string"
}
},
"required": [
"path"
]
}
}
},
{
"type": "function",
"function": {
"name": "developer__list_windows",
"description": "List all available window titles that can be used with screen_capture. Returns a list of window titles that can be used with the window_title parameter of the screen_capture tool.",
"parameters": {
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "developer__screen_capture",
"description": "Capture a screenshot of a specified display or window. You can capture either: 1. A full display (monitor) using the display parameter 2. A specific window by its title using the window_title parameter. Only one of display or window_title should be specified.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ScreenCaptureParams",
"description": "Parameters for the screen_capture tool",
"type": "object",
"properties": {
"display": {
"description": "The display number to capture (0 is main display)",
"type": "integer",
"format": "uint64",
"minimum": 0,
"default": null,
"nullable": true
},
"window_title": {
"description": "Optional: the exact title of the window to capture.\nUse the list_windows tool to find the available windows.",
"type": "string",
"nullable": true
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "developer__shell",
"description": "Execute a command in the shell.This will return the output and error concatenated into a single string, as you would see from running on the command line. There will also be an indication of if the command succeeded or failed. Avoid commands that produce a large amount of output, and consider piping those outputs to files. If you need to run a long lived command, background it - e.g. `uvicorn main:app &` so that this tool does not run indefinitely.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "ShellParams",
"description": "Parameters for the shell tool",
"type": "object",
"properties": {
"command": {
"description": "The command string to execute in the shell",
"type": "string"
}
},
"required": [
"command"
]
}
}
},
{
"type": "function",
"function": {
"name": "developer__text_editor",
"description": "Perform text editing operations on files. Commands: view (show file content), write (create/overwrite file), str_replace (edit file), insert (insert at line), undo_edit (undo last change).",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "TextEditorParams",
"description": "Parameters for the text_editor tool",
"type": "object",
"properties": {
"path": {
"description": "Absolute path to file or directory, e.g. `/repo/file.py` or `/repo`.",
"type": "string"
},
"command": {
"description": "The operation to perform. Allowed options are: `view`, `write`, `str_replace`, `insert`, `undo_edit`.",
"type": "string"
},
"diff": {
"description": "Unified diff to apply. Supports editing multiple files simultaneously. Cannot create or delete files\nExample: \"--- a/file\\n+++ b/file\\n@@ -1,3 +1,3 @@\\n context\\n-old\\n+new\\n context\"\nPreferred edit method.",
"type": "string",
"nullable": true
},
"view_range": {
"description": "Optional array of two integers specifying the start and end line numbers to view.\nLine numbers are 1-indexed, and -1 for the end line means read to the end of the file.\nThis parameter only applies when viewing files, not directories.",
"type": "array",
"items": {
"type": "integer",
"format": "int64"
},
"nullable": true
},
"file_text": {
"description": "The content to write to the file. Required for `write` command.",
"type": "string",
"nullable": true
},
"old_str": {
"description": "The old string to replace.",
"type": "string",
"nullable": true
},
"new_str": {
"description": "The new string to replace with. Required for `insert` command.",
"type": "string",
"nullable": true
},
"insert_line": {
"description": "The line number after which to insert text (0 for beginning). Required for `insert` command.",
"type": "integer",
"format": "int64",
"nullable": true
}
},
"required": [
"path",
"command"
]
}
}
},
{
"type": "function",
"function": {
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "CreateDynamicTaskParams",
"type": "object",
"properties": {
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"type": "array",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1
},
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
}
},
"required": [
"task_parameters"
],
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"type": "object",
"properties": {
"instructions": {
"type": [
"string",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"additionalProperties": true
}
},
"settings": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"parameters": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"additionalProperties": true
}
},
"response": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"retry": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"activities": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
}
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
}
}
}
}
}
}
},
{
"type": "function",
"function": {
"name": "extensionmanager__list_resources",
"description": "List resources from an extension(s).\n\nResources allow extensions to share data that provide context to LLMs, such as\nfiles, database schemas, or application-specific information. This tool lists resources\nin the provided extension, and returns a list for the user to browse. If no extension\nis provided, the tool will search all extensions for the resource.\n",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "ListResourcesParams",
"type": "object",
"properties": {
"extension_name": {
"type": [
"string",
"null"
]
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "extensionmanager__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "ManageExtensionsParams",
"type": "object",
"properties": {
"action": {
"$ref": "#/$defs/ManageExtensionAction"
},
"extension_name": {
"type": "string"
}
},
"required": [
"action",
"extension_name"
],
"$defs": {
"ManageExtensionAction": {
"type": "string",
"enum": [
"enable",
"disable"
]
}
}
}
}
},
{
"type": "function",
"function": {
"name": "extensionmanager__read_resource",
"description": "Read a resource from an extension.\n\nResources allow extensions to share data that provide context to LLMs, such as\nfiles, database schemas, or application-specific information. This tool searches for the\nresource URI in the provided extension, and reads in the resource content. If no extension\nis provided, the tool will search all extensions for the resource.\n",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "ReadResourceParams",
"type": "object",
"properties": {
"uri": {
"type": "string"
},
"extension_name": {
"type": [
"string",
"null"
]
}
},
"required": [
"uri"
]
}
}
},
{
"type": "function",
"function": {
"name": "extensionmanager__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"parameters": {
"type": "object",
"required": [],
"properties": {}
}
}
},
{
"type": "function",
"function": {
"name": "fetch__fetch",
"description": "Fetches a URL from the internet and optionally extracts its contents as markdown.\n\nAlthough originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.",
"parameters": {
"description": "Parameters for fetching a URL.",
"properties": {
"url": {
"description": "URL to fetch",
"format": "uri",
"minLength": 1,
"title": "Url",
"type": "string"
},
"max_length": {
"default": 5000,
"description": "Maximum number of characters to return.",
"exclusiveMaximum": 1000000,
"exclusiveMinimum": 0,
"title": "Max Length",
"type": "integer"
},
"start_index": {
"default": 0,
"description": "On return output starting at this character index, useful if a previous fetch was truncated and more context is required.",
"minimum": 0,
"title": "Start Index",
"type": "integer"
},
"raw": {
"default": false,
"description": "Get the actual HTML content of the requested page, without simplification.",
"title": "Raw",
"type": "boolean"
}
},
"required": [
"url"
],
"title": "Fetch",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "gotohumanmcpserver__get-form-schema",
"description": "Get the schema to use for the 'fields' property when requesting a human review with a form.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"formId": {
"description": "The form ID to fetch the schema for",
"type": "string"
}
},
"required": [
"formId"
]
}
}
},
{
"type": "function",
"function": {
"name": "gotohumanmcpserver__list-forms",
"description": "List all available review forms. NOTE: You need to fetch the schema for the form fields first using the get-form-schema tool.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "gotohumanmcpserver__request-human-review-with-form",
"description": "Request a human review with a form. NOTE: If you don't have a form ID yet, list all available forms using the list-forms tool first. To know what to pass for fieldData, you need to fetch the schema for the form fields using the get-form-schema tool.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"formId": {
"description": "The form ID to request a human review for",
"type": "string"
},
"fieldData": {
"description": "The field data to include in the review request. Note that this is a dynamic schema that you need to fetch first using the get-form-schema tool.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"properties": {},
"required": []
},
"metadata": {
"description": "Optional additional data that will be incl. in the webhook response after form submission. Incl. everything required to proceed with your workflow.",
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
},
"properties": {},
"required": []
},
"assignToUsers": {
"description": "Optional list of user emails to assign the review to",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"formId",
"fieldData"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__add_observations",
"description": "Add new observations to existing entities in the knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"observations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"entityName": {
"description": "The name of the entity to add the observations to",
"type": "string"
},
"contents": {
"description": "An array of observation contents to add",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"entityName",
"contents"
]
}
}
},
"required": [
"observations"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__create_entities",
"description": "Create multiple new entities in the knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"entities": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"description": "The name of the entity",
"type": "string"
},
"entityType": {
"description": "The type of the entity",
"type": "string"
},
"observations": {
"description": "An array of observation contents associated with the entity",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"name",
"entityType",
"observations"
]
}
}
},
"required": [
"entities"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__create_relations",
"description": "Create multiple new relations between entities in the knowledge graph. Relations should be in active voice",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"relations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"from": {
"description": "The name of the entity where the relation starts",
"type": "string"
},
"to": {
"description": "The name of the entity where the relation ends",
"type": "string"
},
"relationType": {
"description": "The type of the relation",
"type": "string"
}
},
"required": [
"from",
"to",
"relationType"
]
}
}
},
"required": [
"relations"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__delete_entities",
"description": "Delete multiple entities and their associated relations from the knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"entityNames": {
"description": "An array of entity names to delete",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"entityNames"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__delete_observations",
"description": "Delete specific observations from entities in the knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"deletions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"entityName": {
"description": "The name of the entity containing the observations",
"type": "string"
},
"observations": {
"description": "An array of observations to delete",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"entityName",
"observations"
]
}
}
},
"required": [
"deletions"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__delete_relations",
"description": "Delete multiple relations from the knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"relations": {
"description": "An array of relations to delete",
"type": "array",
"items": {
"type": "object",
"properties": {
"from": {
"description": "The name of the entity where the relation starts",
"type": "string"
},
"to": {
"description": "The name of the entity where the relation ends",
"type": "string"
},
"relationType": {
"description": "The type of the relation",
"type": "string"
}
},
"required": [
"from",
"to",
"relationType"
]
}
}
},
"required": [
"relations"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__open_nodes",
"description": "Open specific nodes in the knowledge graph by their names",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"names": {
"description": "An array of entity names to retrieve",
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"names"
]
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__read_graph",
"description": "Read the entire knowledge graph",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "knowledgegraphmemory__search_nodes",
"description": "Search for nodes in the knowledge graph based on a query",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"query": {
"description": "The search query to match against entity names, types, and observation content",
"type": "string"
}
},
"required": [
"query"
]
}
}
},
{
"type": "function",
"function": {
"name": "memory__remember_memory",
"description": "Stores a memory with optional tags in a specified category",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RememberMemoryParams",
"description": "Parameters for the remember_memory tool",
"type": "object",
"properties": {
"category": {
"description": "The category to store the memory in",
"type": "string"
},
"data": {
"description": "The data to remember",
"type": "string"
},
"tags": {
"description": "Optional tags for the memory",
"type": "array",
"items": {
"type": "string"
},
"default": []
},
"is_global": {
"description": "Whether to store globally or locally",
"type": "boolean"
}
},
"required": [
"category",
"data",
"is_global"
]
}
}
},
{
"type": "function",
"function": {
"name": "memory__remove_memory_category",
"description": "Removes all memories within a specified category",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RemoveMemoryCategoryParams",
"description": "Parameters for the remove_memory_category tool",
"type": "object",
"properties": {
"category": {
"description": "The category to remove (use \"*\" for all)",
"type": "string"
},
"is_global": {
"description": "Whether to remove from global or local storage",
"type": "boolean"
}
},
"required": [
"category",
"is_global"
]
}
}
},
{
"type": "function",
"function": {
"name": "memory__remove_specific_memory",
"description": "Removes a specific memory within a specified category",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RemoveSpecificMemoryParams",
"description": "Parameters for the remove_specific_memory tool",
"type": "object",
"properties": {
"category": {
"description": "The category containing the memory",
"type": "string"
},
"memory_content": {
"description": "The content of the memory to remove",
"type": "string"
},
"is_global": {
"description": "Whether to remove from global or local storage",
"type": "boolean"
}
},
"required": [
"category",
"memory_content",
"is_global"
]
}
}
},
{
"type": "function",
"function": {
"name": "memory__retrieve_memories",
"description": "Retrieves all memories from a specified category",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "RetrieveMemoriesParams",
"description": "Parameters for the retrieve_memories tool",
"type": "object",
"properties": {
"category": {
"description": "The category to retrieve memories from (use \"*\" for all)",
"type": "string"
},
"is_global": {
"description": "Whether to retrieve from global or local storage",
"type": "boolean"
}
},
"required": [
"category",
"is_global"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__add_bookmark",
"description": "Add a new bookmark (Extension required)",
"parameters": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "Title of the bookmark"
},
"url": {
"type": "string",
"description": "URL of the bookmark"
},
"parentId": {
"type": "string",
"description": "ID of the parent folder (optional)"
}
},
"required": [
"title",
"url"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__element_click",
"description": "🖱️ BACKGROUND TAB READY: Click elements in any tab without switching! Perform actions on background tabs while staying on current page. Use tab_id to target specific tabs. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"element_id": {
"type": "string",
"description": "Element ID from page_analyze"
},
"click_type": {
"type": "string",
"enum": [
"left",
"right",
"double"
],
"default": "left"
}
},
"required": [
"element_id"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__element_fill",
"description": "✏️ BACKGROUND TAB READY: Fill forms in any tab without switching! Enhanced focus and event simulation for modern web apps with anti-detection bypass for Twitter/X, LinkedIn, Facebook. Use tab_id to fill forms in background tabs. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"element_id": {
"type": "string",
"description": "Element ID from page_analyze"
},
"value": {
"type": "string",
"description": "Text to input"
},
"clear_first": {
"type": "boolean",
"default": true,
"description": "Clear existing content before filling"
}
},
"required": [
"element_id",
"value"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__element_get_state",
"description": "🔍 Get detailed state information for a specific element (disabled, clickable, etc.) (Extension required)",
"parameters": {
"type": "object",
"properties": {
"element_id": {
"type": "string",
"description": "Element ID from page_analyze"
}
},
"required": [
"element_id"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__get_bookmarks",
"description": "Get all bookmarks or search for specific bookmarks (Extension required)",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query for bookmarks (optional)"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__get_history",
"description": "🕒 Search browser history with comprehensive filters for finding previous work (Extension required)",
"parameters": {
"type": "object",
"properties": {
"keywords": {
"type": "string",
"description": "Search keywords to match in page titles and URLs"
},
"start_date": {
"type": "string",
"format": "date-time",
"description": "Start date for history search (ISO 8601 format)"
},
"end_date": {
"type": "string",
"format": "date-time",
"description": "End date for history search (ISO 8601 format)"
},
"domains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Filter by specific domains"
},
"min_visit_count": {
"type": "number",
"default": 1,
"description": "Minimum visit count threshold"
},
"max_results": {
"type": "number",
"default": 50,
"maximum": 500,
"description": "Maximum number of results to return"
},
"sort_by": {
"type": "string",
"enum": [
"visit_time",
"visit_count",
"title"
],
"default": "visit_time",
"description": "Sort results by visit time, visit count, or title"
},
"sort_order": {
"type": "string",
"enum": [
"desc",
"asc"
],
"default": "desc",
"description": "Sort order"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__get_page_links",
"description": "🔗 Get all hyperlinks on the current page with smart filtering (Extension required)",
"parameters": {
"type": "object",
"properties": {
"include_internal": {
"type": "boolean",
"default": true,
"description": "Include internal links (same domain)"
},
"include_external": {
"type": "boolean",
"default": true,
"description": "Include external links (different domains)"
},
"domain_filter": {
"type": "string",
"description": "Filter links to include only specific domain(s)"
},
"max_results": {
"type": "number",
"default": 100,
"maximum": 500,
"description": "Maximum number of links to return"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__get_selected_text",
"description": "📝 BACKGROUND TAB READY: Get selected text from any tab without switching! Perfect for collecting quotes, citations, or highlighted content from multiple research tabs simultaneously. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"include_metadata": {
"type": "boolean",
"default": true,
"description": "Include metadata about the selection (element info, position, etc.)"
},
"max_length": {
"type": "number",
"default": 10000,
"description": "Maximum length of text to return"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_analyze",
"description": "🔍 BACKGROUND TAB READY: Analyze any tab without switching! Two-phase intelligent page analysis with token efficiency optimization. Use tab_id parameter to analyze background tabs while staying on current page. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"intent_hint": {
"type": "string",
"description": "What user wants to do: post_tweet, search, login, etc."
},
"phase": {
"type": "string",
"enum": [
"discover",
"detailed"
],
"default": "discover",
"description": "Analysis phase: 'discover' for quick scan, 'detailed' for full analysis"
}
},
"required": [
"intent_hint"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_extract_content",
"description": "📄 BACKGROUND TAB READY: Extract content from any tab without switching! Perfect for analyzing multiple research tabs, articles, or pages simultaneously. Use tab_id to target specific background tabs. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"content_type": {
"type": "string",
"enum": [
"article",
"search_results",
"posts"
],
"description": "Type of content to extract"
},
"summarize": {
"type": "boolean",
"default": true,
"description": "Return summary instead of full content (saves tokens)"
}
},
"required": [
"content_type"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_navigate",
"description": "🧭 Navigate to URLs with wait conditions (Extension required)",
"parameters": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to navigate to"
},
"wait_for": {
"type": "string",
"description": "CSS selector to wait for after navigation"
}
},
"required": [
"url"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_scroll",
"description": "📜 BACKGROUND TAB READY: Scroll any tab without switching! Critical for long pages. Navigate through content in background tabs while staying on current page. Use tab_id to target specific tabs. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": [
"up",
"down",
"left",
"right",
"top",
"bottom"
],
"default": "down",
"description": "Direction to scroll"
},
"amount": {
"type": "string",
"enum": [
"small",
"medium",
"large",
"page",
"custom"
],
"default": "medium",
"description": "Amount to scroll"
},
"pixels": {
"type": "number",
"description": "Custom pixel amount (when amount is 'custom')"
},
"smooth": {
"type": "boolean",
"default": true,
"description": "Use smooth scrolling animation"
},
"element_id": {
"type": "string",
"description": "Scroll to specific element (overrides direction/amount)"
},
"wait_after": {
"type": "number",
"default": 500,
"description": "Milliseconds to wait after scrolling"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_style",
"description": "🎨 Transform page appearance with themes, colors, fonts, and fun effects! Apply preset themes like 'dark_hacker', 'retro_80s', or create custom styles. Perfect for making boring pages fun or improving readability.",
"parameters": {
"type": "object",
"examples": [
{
"mode": "preset",
"theme": "dark_hacker"
},
{
"mode": "custom",
"background": "#000",
"text_color": "#00ff00",
"font": "monospace"
},
{
"mode": "ai_mood",
"mood": "cozy coffee shop vibes",
"intensity": "strong"
},
{
"mode": "effect",
"effect": "matrix_rain",
"duration": 30
}
],
"properties": {
"mode": {
"type": "string",
"enum": [
"preset",
"custom",
"ai_mood",
"effect",
"reset"
],
"description": "Styling mode to use"
},
"theme": {
"type": "string",
"enum": [
"dark_hacker",
"retro_80s",
"rainbow_party",
"minimalist_zen",
"high_contrast",
"cyberpunk",
"pastel_dream",
"newspaper"
],
"description": "Preset theme name (when mode=preset)"
},
"background": {
"type": "string",
"description": "Background color/gradient"
},
"text_color": {
"type": "string",
"description": "Text color"
},
"font": {
"type": "string",
"description": "Font family"
},
"font_size": {
"type": "string",
"description": "Font size (e.g., '1.2em', '16px')"
},
"mood": {
"type": "string",
"description": "Describe desired mood/feeling (when mode=ai_mood)"
},
"intensity": {
"type": "string",
"enum": [
"subtle",
"medium",
"strong"
],
"default": "medium"
},
"effect": {
"type": "string",
"enum": [
"matrix_rain",
"floating_particles",
"cursor_trail",
"neon_glow",
"typing_effect"
]
},
"duration": {
"type": "number",
"description": "Effect duration in seconds",
"default": 10
},
"remember": {
"type": "boolean",
"description": "Remember this style for this website",
"default": false
}
},
"required": [
"mode"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__page_wait_for",
"description": "⏳ Wait for elements or conditions (Extension required)",
"parameters": {
"type": "object",
"properties": {
"condition_type": {
"type": "string",
"enum": [
"element_visible",
"text_present"
],
"description": "Type of condition to wait for"
},
"selector": {
"type": "string",
"description": "CSS selector (for element_visible condition)"
},
"text": {
"type": "string",
"description": "Text to wait for (for text_present condition)"
}
},
"required": [
"condition_type"
]
}
}
},
{
"type": "function",
"function": {
"name": "opendia__tab_close",
"description": "❌ Close specific tab(s) by ID or close current tab (Extension required)",
"parameters": {
"type": "object",
"properties": {
"tab_id": {
"type": "number",
"description": "Specific tab ID to close (optional, closes current tab if not provided)"
},
"tab_ids": {
"type": "array",
"items": {
"type": "number"
},
"description": "Array of tab IDs to close multiple tabs"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__tab_create",
"description": "Creates tabs. CRITICAL: For multiple identical tabs, ALWAYS use 'count' parameter! Examples: {url: 'https://x.com', count: 5} creates 5 Twitter tabs. {url: 'https://github.com', count: 10} creates 10 GitHub tabs. Single tab: {url: 'https://example.com'}. Multiple different URLs: {urls: ['url1', 'url2']}.",
"parameters": {
"type": "object",
"examples": [
{
"url": "https://x.com",
"count": 5
},
{
"url": "https://github.com",
"count": 10
},
{
"urls": [
"https://x.com/post1",
"https://x.com/post2",
"https://google.com"
]
},
{
"url": "https://example.com"
}
],
"properties": {
"url": {
"type": "string",
"description": "Single URL to open. Can be used with 'count' to create multiple identical tabs"
},
"urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "PREFERRED FOR MULTIPLE URLS: Array of URLs to open ALL AT ONCE in a single batch operation. Pass ALL URLs here instead of making multiple calls! Example: ['https://x.com/post1', 'https://x.com/post2', 'https://google.com']",
"maxItems": 100
},
"count": {
"type": "number",
"default": 1,
"minimum": 1,
"maximum": 50,
"description": "REQUIRED FOR MULTIPLE IDENTICAL TABS: Set this to N to create N copies of the same URL. For '5 Twitter tabs' use count=5 with url='https://x.com'. DO NOT make 5 separate calls!"
},
"active": {
"type": "boolean",
"default": true,
"description": "Whether to activate the last created tab (single tab only)"
},
"wait_for": {
"type": "string",
"description": "CSS selector to wait for after tab creation (single tab only)"
},
"timeout": {
"type": "number",
"default": 10000,
"description": "Maximum wait time per tab in milliseconds"
},
"batch_settings": {
"type": "object",
"description": "Performance control settings for batch operations",
"properties": {
"chunk_size": {
"type": "number",
"default": 5,
"minimum": 1,
"maximum": 10,
"description": "Number of tabs to create per batch"
},
"delay_between_chunks": {
"type": "number",
"default": 1000,
"minimum": 100,
"maximum": 5000,
"description": "Delay between batches in milliseconds"
},
"delay_between_tabs": {
"type": "number",
"default": 200,
"minimum": 50,
"maximum": 1000,
"description": "Delay between individual tabs in milliseconds"
}
},
"required": []
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__tab_list",
"description": "📋 TAB DISCOVERY: Get list of all open tabs with IDs for background tab targeting! Shows content script readiness status and tab details. Essential for multi-tab workflows - use tab IDs with other tools to work on background tabs. (Extension required)",
"parameters": {
"type": "object",
"properties": {
"current_window_only": {
"type": "boolean",
"default": true,
"description": "Only return tabs from the current window"
},
"include_details": {
"type": "boolean",
"default": true,
"description": "Include additional tab details (title, favicon, etc.)"
}
},
"required": []
}
}
},
{
"type": "function",
"function": {
"name": "opendia__tab_switch",
"description": "🔄 Switch to a specific tab by ID (Extension required)",
"parameters": {
"type": "object",
"properties": {
"tab_id": {
"type": "number",
"description": "Tab ID to switch to"
}
},
"required": [
"tab_id"
]
}
}
},
{
"type": "function",
"function": {
"name": "pdfreader__read_pdf",
"description": "\n Use this anytime you need to read a PDF file and extract its text.\n Works with both protected and unprotected PDFs, complex and large PDFs.\n Instead of returning the text directly, writes content to a single temporary file and returns the file path.\n This will work with very large and complex PDFs\n\n Args:\n file_path: Path to the PDF file, this MUST be an absolute path on the filesystem.\n password: Optional password to decrypt the PDF if it's protected\n pages: Optional list of specific page numbers to extract (1-indexed). If None, all pages are extracted.\n\n Returns:\n json containing path to extracted text content file and metadata\n The file returned may be large so use tools like ripgrep to search it\n ",
"parameters": {
"properties": {
"file_path": {
"title": "File Path",
"type": "string"
},
"password": {
"default": null,
"title": "Password",
"type": "string"
},
"pages": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Pages"
}
},
"required": [
"file_path"
],
"title": "read_pdfArguments",
"type": "object"
}
}
},
{
"type": "function",
"function": {
"name": "platform__manage_schedule",
"description": "Manage scheduled recipe execution for this goose instance.\n\nActions:\n- \"list\": List all scheduled jobs\n- \"create\": Create a new scheduled job from a recipe file\n- \"run_now\": Execute a scheduled job immediately \n- \"pause\": Pause a scheduled job\n- \"unpause\": Resume a paused job\n- \"delete\": Remove a scheduled job\n- \"kill\": Terminate a currently running job\n- \"inspect\": Get details about a running job\n- \"sessions\": List execution history for a job\n- \"session_content\": Get the full content (messages) of a specific session\n",
"parameters": {
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"type": "string",
"enum": [
"list",
"create",
"run_now",
"pause",
"unpause",
"delete",
"kill",
"inspect",
"sessions",
"session_content"
]
},
"job_id": {
"type": "string",
"description": "Job identifier for operations on existing jobs"
},
"recipe_path": {
"type": "string",
"description": "Path to recipe file for create action"
},
"cron_expression": {
"type": "string",
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds."
},
"limit": {
"type": "integer",
"description": "Limit for sessions list",
"default": 50
},
"session_id": {
"type": "string",
"description": "Session identifier for session_content action"
}
}
}
}
},
{
"type": "function",
"function": {
"name": "skills__loadSkill",
"description": "Load a skill by name and return its content.\n\nThis tool loads the specified skill and returns its body content along with\ninformation about any supporting files in the skill directory.\n",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "LoadSkillParams",
"type": "object",
"properties": {
"name": {
"type": "string"
}
},
"required": [
"name"
]
}
}
},
{
"type": "function",
"function": {
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
"parameters": {
"type": "object",
"properties": {
"execution_mode": {
"type": "string",
"enum": [
"sequential",
"parallel"
],
"default": "sequential",
"description": "Execution strategy for multiple tasks. Use 'sequential' (default) unless user explicitly requests parallel execution with words like 'parallel', 'simultaneously', 'at the same time', or 'concurrently'."
},
"task_ids": {
"type": "array",
"items": {
"type": "string",
"description": "Unique identifier for the task"
}
}
},
"required": [
"task_ids"
]
}
}
},
{
"type": "function",
"function": {
"name": "todo__todo_write",
"description": "Overwrite the entire TODO content.\n\nThe content persists across conversation turns and compaction. Use this for:\n- Task tracking and progress updates\n- Important notes and reminders\n\nWARNING: This operation completely replaces the existing content. Always include\nall content you want to keep, not just the changes.\n",
"parameters": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "TodoWriteParams",
"type": "object",
"properties": {
"content": {
"type": "string"
}
},
"required": [
"content"
]
}
}
},
{
"type": "function",
"function": {
"name": "tutorial__load_tutorial",
"description": "Load a specific tutorial by name. The tutorial will be returned as markdown content that provides step by step instructions.",
"parameters": {
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "LoadTutorialParams",
"description": "Parameters for the load_tutorial tool",
"type": "object",
"properties": {
"name": {
"description": "Name of the tutorial to load, e.g. 'getting-started' or 'developer-mcp'",
"type": "string"
}
},
"required": [
"name"
]
}
}
}
]