> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom Tools Integration

> Learn how to create and integrate custom tools with your AI agent using the @register_tool decorator

<AccordionGroup>
  <Accordion title="Prerequisites">
    ### Virtual Environment Setup

    ```bash setup.sh theme={"dark"}
    python3 -m venv .venv
    source .venv/bin/activate
    pip install "xpander-sdk[agno]"
    ```

    ### Environment Setup

    The `.env` file is created when you download your agent code:

    ```bash theme={"dark"}
    xpander init
    ```

    This downloads your agent code from the platform with the `.env` file pre-configured with your keys.
  </Accordion>
</AccordionGroup>

```python custom_tools_example.py theme={"dark"}
from dotenv import load_dotenv
load_dotenv()

from xpander_sdk import Backend, register_tool
from agno.agent import Agent

@register_tool 
def weather_check(location: str) -> str:
    """Check weather for a location"""
    return f"Weather in {location}: Sunny, 25°C"

backend = Backend()
agno_agent = Agent(**backend.get_args())

agno_agent.print_response(message="What's the weather in Tel Aviv?")
```

## How to Run

```bash custom_tools_example.py theme={"dark"}
python custom_tools_example.py
```

This example shows automatic tool discovery where the agent recognizes it needs weather information, calls the custom `weather_check` tool seamlessly during conversation, and uses the tool's response to provide a complete answer. Tools are registered with type hints and docstrings that help the AI understand their purpose and usage.

## Production Deployment

For creating and deploying agents to production, see the [Setup and Deployment Guide](/Examples/00-setup-deployment).