- Home
- Skills
- Agents & Orchestration
- Freebies — Tool Calling Schema Builder
Works with the AI Agents you already use
Freebies — Tool Calling Schema Builder
Convert native function signatures into cross-platform JSON Schema tool definitions for OpenAI, Claude, and Gemini.
Free
Freebies — Tool Calling Schema Builder
Example session with this skill installed
Convert this Python function into an Anthropic Claude tool schema: def get_weather(location: str, unit: str = 'celsius'): \"\"\"Fetch current weather for a city.\"\"\"
- Read your context and instructions
- Compiled the freebies
I have parsed the `get_weather` function and generated the Anthropic-compatible tool definition. ## Anthropic Tool Schema ```json { "name": "get_weather", "description": "Fetch current weather for a city.", "input_schema": { "type": "object", "properties": { "location": { "type": "string", "description": "The city name and state/country, e.g., 'San Francisco, CA'" }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"], "default": "celsius", "description": "The temperature unit to return results in" } }, "required": ["location"] } } ``` **Next steps** - Verify if `unit` should be an optional parameter in your client-side implementation. - Copy this JSON into your `tools` array in the Anthropic API request. - Run a test call to ensure the model correctly identifies the `location` string.
Connects securely to your tools. The creator never sees your data.
About this skill
Manually writing JSON Schema definitions for LLM tools is repetitive and prone to syntax errors that cause runtime failures. This skill automates the conversion of native function signatures into validated tool definitions for major AI providers. ## What it does - **Multi-provider formatting** generates schemas specific to OpenAI Function Calling, Anthropic Claude Tools, Gemini, or MCP. - **Automated parsing** extracts parameter types, default values, and docstrings directly from native code. - **Semantic mapping** ensures parameter descriptions provide clear guidance to prevent LLM hallucinations. - **Validation enforcement** builds explicit property types and required field arrays to meet strict JSON Schema specs. ## How it works 1. **Parse Function Parameters**: Submit a native function signature or block of code for analysis. 2. **Construct JSON**: The skill builds a structured object mapping native types to JSON Schema equivalents. 3. **Format for Target**: Specify the provider (e.g., Anthropic or OpenAI) to wrap the schema in the correct envelope. 4. **Refine Descriptions**: The skill injects semantic context into descriptions to improve agent reliability. ## Frameworks & tools Works with OpenAI, Anthropic Claude, Google Gemini, and Model Context Protocol (MCP). Compatible with Claude Code, Cursor, Windsurf, and Agent SDKs. ## Why this beats prompting it yourself Generic prompts often miss "required" arrays or fail to map complex types like enums and nested objects correctly for specific API versions. This skill follows a deterministic workflow to ensure cross-platform compatibility and zero circular references. ## Use cases - Convert Python type-hinted functions into MCP server tool definitions. - Generate Anthropic-compatible tool schemas from legacy JavaScript modules. - Batch transform API documentation into OpenAI function calling JSON objects. ## Known limitations Does not support circular references within the JSON Schema. All operations are confined to the local workspace.
Restricted to local workspace operations. Does not support circular references in JSON Schema structures.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires
Permissions
Target Use Cases: - Convert this function into an LLM tool calling schema. - Create JSON Schema for OpenAI function calling. - Build Anthropic tool definition from Python function.