# Tool calling

Declare local functions, execute them in your application, and return results to the model.

Tool calling lets a model request a function that your application executes. KosCompute never executes the function for you.

## 1. Declare the tool

```json
{
  "model": "qwen/qwen3.8-27b",
  "messages": [{"role": "user", "content": "What is the weather in Brno?"}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Return current weather for a city",
      "parameters": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"],
        "additionalProperties": false
      }
    }
  }],
  "tool_choice": "auto",
  "max_completion_tokens": 400
}
```

## 2. Execute the call

Read `choices[0].message.tool_calls`. Parse each function's `arguments` JSON, validate it again in your application, apply authorization, and execute the local function. Never treat model-generated arguments as trusted input.

## 3. Return the result

Append the assistant message containing `tool_calls`, then append a tool message with the matching ID:

```json
{"role":"tool","tool_call_id":"call_abc123","content":"{\"temperature_c\":21}"}
```

Send the expanded conversation in a second completion request.

## Tool choice

`auto` lets the model decide, `none` prevents a call, `required` requests a call, and a named function selects one tool. Backend behavior for `required` can be model-specific. In particular, some routes can guarantee required choice only with one named function; the Responses adapter rejects combinations it cannot guarantee instead of pretending they are equivalent.

Responses uses `function_call` output items and `function_call_output` input items joined by `call_id`. See the [Responses guide](/docs/guides/responses-api/) for that shape.