Agent with Tools

Give a Mistral agent a custom function tool.

The weather tool returns static example data so you can follow the function-call flow. Connect a weather service to return live conditions.

Code

import asyncio
import json

from agno.agent import Agent
from agno.models.mistral import MistralChat
from agno.tools import tool

@tool
def get_weather(city: str) -> str:
    """Get the current weather for a city.

    Args:
        city: The city name to get weather for.
    """
    weather_data = {
        "Paris": {"temp": 18, "condition": "cloudy", "humidity": 65},
        "London": {"temp": 14, "condition": "rainy", "humidity": 80},
        "Tokyo": {"temp": 22, "condition": "sunny", "humidity": 50},
        "New York": {"temp": 20, "condition": "partly cloudy", "humidity": 55},
    }
    data = weather_data.get(city, {"temp": 20, "condition": "unknown", "humidity": 50})
    return json.dumps(data)

agent = Agent(
    model=MistralChat(id="mistral-large-latest"),
    tools=[get_weather],
    markdown=True,
)

if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("What is the weather in Paris and Tokyo?")

    # --- Async ---
    asyncio.run(agent.aprint_response("What is the weather in London and New York?"))

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export MISTRAL_API_KEY=xxx

Install dependencies

uv pip install -U mistralai agno

Run Agent

Save the code above as tool_use.py, then run:

python tool_use.py