# Tool calling

Tool calling returns structured requests for your code to execute. Zrelay does not execute your functions.

Source: https://zrelay.net/docs/capabilities/tool-calling/

## Define a tool

```
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather in Madrid?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Read weather for a city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string"
            }
          },
          "required": [
            "city"
          ],
          "additionalProperties": false
        }
      }
    }
  ]
}
```

## Validate and execute

Read `message.tool_calls`, validate each function name and parse its JSON arguments against your schema. Apply permissions in your application before executing. Treat tool output and model arguments as untrusted data.

## Return results to the model

For Chat Completions, append the assistant message containing the calls, then a `role: tool` message for each result with the matching `tool_call_id`. Send the conversation again to obtain a final answer. Messages and Responses use their own tool result formats.

## Bound the loop

Limit iterations, execution time and spend. Require explicit approval for destructive or external effects. Retry only operations whose effects you can safely identify or deduplicate; a repeated model request can propose the same action again.