> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tai42.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Build a tool

> Register a Python function as a tool.

Write a plain Python function, register it, and load it from the manifest as a tool.

A tool is the atom of work — a plain Python function the runtime exposes as an MCP tool. You write the function, decorate it with `@tai42_app.tools.tool`, and name its module in the manifest. Importing the module runs the decorator, which registers the tool on the server.

## Write the tool module

Put your function in a module in your own package and register it through the `tai42_app` handle. The decorator returns the function unchanged, so the module stays ordinary Python.

```python myapp/tools.py theme={null}
from tai42_contract.app import tai42_app


@tai42_app.tools.tool
def greet(name: str) -> str:
    """Greet a person by name."""
    return f"Hello, {name}!"
```

The function's signature becomes the tool's input schema and its docstring becomes the tool description, so annotate the parameters and write a real docstring.

## Load it from the manifest

Name the module under `tools[].module`. Each entry imports the module; `include` filters which tool names to expose (omit it to expose every tool the module defines).

```yaml manifest.yml theme={null}
tools:
  - title: hello
    module: myapp.tools
    include: [greet]
```

The module must be importable from the server process, so keep your package on `PYTHONPATH`.

## Run and call it

<Steps>
  <Step title="Start the server">
    Point the server at your manifest and start it.

    ```bash theme={null}
    tai serve --manifest-path manifest.yml
    ```
  </Step>

  <Step title="Confirm it registered">
    List the registered tools and inspect one tool's schema.

    ```bash theme={null}
    tai tools list
    tai tools schema greet
    ```
  </Step>

  <Step title="Run it">
    Call the tool synchronously and print its result. Pass arguments with the repeatable `--kw key=value` (each value is parsed as JSON), or a whole JSON object with `--kwargs`.

    ```bash theme={null}
    tai tools run greet --kw name=Ada
    ```
  </Step>
</Steps>

<Tip>
  Long-running work does not have to block a request. Submit a detached run with `tai tools runs submit`, then poll it with `tai tools runs get`.
</Tip>

## See also

* [Tools and extensions](/concepts/tools-and-extensions) — what a tool is and how an extension wraps one.
* [The manifest](/concepts/manifest) — every section a server loads at startup.
* [Apply an extension](/guides/apply-an-extension) — clip a wrapper or transformer onto a tool.
* [CLI reference](/reference/cli) — the full `tai tools` surface.