Defining & Executing Tools

Passing Tools to Models

To let an LLM use a tool, you define its signature using a JSON Schema. The LLM doesn't execute the code—it asks you to execute it.

{
  "name": "get_weather",
  "description": "Get the current weather in a given location.",
  "input_schema": {
    "type": "object",
    "properties": {
      "location": { "type": "string", "description": "City name" }
    },
    "required": ["location"]
  }
}

The Handshake

1. Send prompt + tools array.
2. Model responds with tool_use intent (e.g., location="Tokyo").
3. Your code executes get_weather("Tokyo").
4. You send the result back as a tool_result message.