# Mistral Structured Output With Tool Use (/examples/models/mistral/structured-output-with-tool-use)



This model configuration sends a JSON Schema request. Agno then parses the returned content against the Pydantic schema; check its type before reading model fields.

```python title="structured_output_with_tool_use.py"
"""
Mistral Structured Output With Tool Use
=======================================

Cookbook example for `mistral/structured_output_with_tool_use.py`.
"""

from agno.agent import Agent
from agno.models.mistral import MistralChat
from agno.tools.websearch import WebSearchTools
from pydantic import BaseModel

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


class Person(BaseModel):
    name: str
    description: str


model = MistralChat(
    id="mistral-medium-latest",
    temperature=0.0,
)

researcher = Agent(
    name="Researcher",
    model=model,
    role="You find people with a specific role at a provided company.",
    instructions=[
        "- Search the web for the person described"
        "- Find out if they have public contact details"
        "- Return the information in a structured format"
    ],
    tools=[WebSearchTools()],
    output_schema=Person,
    add_datetime_to_context=True,
)

researcher.print_response("Find information about Elon Musk")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

<Note>
  `output_schema` describes the expected type. If parsing or validation fails, `result.content` can remain a string. Before accessing schema fields in a run result, use `isinstance(result.content, YourSchema)`, replacing `YourSchema` with the class you passed as `output_schema`.
</Note>

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno ddgs mistralai
    ```
  </Step>

  <Step title="Export your Mistral API key">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export MISTRAL_API_KEY="your_mistral_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```powershell
        $Env:MISTRAL_API_KEY="your_mistral_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

  <Step title="Run the example">
    Save the code above as `structured_output_with_tool_use.py`, then run:

    ```bash
    python structured_output_with_tool_use.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/mistral/structured\_output\_with\_tool\_use.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/90_models/mistral/structured_output_with_tool_use.py)