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

# Tools

> What an agent can do, and how a tool is configured per agent.

A tool is a Python function an agent may call. The core ships a portfolio of **31 tool
modules**; an agent is given the subset it needs, and each tool that talks to an external
service reads its settings from a **tool configuration** attached to that agent.

## The portfolio

| Family             | Modules                                                                                          |
| ------------------ | ------------------------------------------------------------------------------------------------ |
| Google Workspace   | `google_auth`, `google_drive`, `google_gmail`, `google_calendar`, `google_docs`, `google_sheets` |
| Microsoft 365      | `microsoft_auth`, `outlook_mail`, `teams`, `onedrive_core`, `onedrive_read`, `onedrive_write`    |
| Data and databases | `database`, `database_mcp`, `data_handler`, `text_to_sql`, `s3_tools`, `db_to_rag`               |
| BI and visuals     | `business_intelligence`, `visualization`, `image_generation`                                     |
| Knowledge          | `rag`, `memory`                                                                                  |
| External services  | `api_call`, `web_search_mcp`, `odoo`, `marketing`, `thaink2`                                     |
| Media              | `audio`                                                                                          |
| Utilities          | `basic`, `integration_status`                                                                    |

Ask a running instance rather than trusting this table to stay exhaustive:

| Method | Endpoint                        | Description                               |
| ------ | ------------------------------- | ----------------------------------------- |
| GET    | `/api/tools`                    | Every tool available to the caller        |
| GET    | `/api/tools/docs`               | Their documentation, as the agent sees it |
| GET    | `/api/tools/{tool_name}/params` | The parameters one tool expects           |

## Tool configurations

A tool module is generic; a tool *configuration* binds it to something concrete — this
database, that Drive folder, this API key. Configurations belong to an agent, so two
agents can use `database` against two different servers.

| Method | Endpoint                             | Description         |
| ------ | ------------------------------------ | ------------------- |
| GET    | `/api/tools_config`                  | List configurations |
| POST   | `/api/tools_config`                  | Create one          |
| GET    | `/api/tools_config/{tool_config_id}` | Read one            |
| PUT    | `/api/tools_config/{tool_config_id}` | Update one          |
| DELETE | `/api/tools_config/{tool_config_id}` | Delete one          |

Credentials inside a configuration are encrypted at rest with `ENCRYPT_KEY`.

<Note>
  Tools that act on Google or Microsoft data do **not** hold their own credentials: they
  use the OAuth integration the user connected, so revoking the integration revokes the
  agent's access with it. See [Integrations](/guides/integrations/overview).
</Note>

## Tools backed by MCP

Two modules are not plain functions but MCP toolsets: `database_mcp` and
`web_search_mcp`. They are discovered by naming convention — a factory called
`mcp_tool_set_*` is invoked at build time so the toolset is created fresh, with the
current key, rather than captured once at import. See [MCP](/guides/mcp).

## Adding a tool

A module in the portfolio exposes plain functions with type hints and a docstring — that
docstring is what the model reads to decide whether to call it, so it is interface, not
commentary. Reload the agent (`POST /api/agents/{agent_id}/reload`) to pick up a change
without restarting the server.