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

# Agentic Tools

> Let the interactive CLI chat fetch live pages and call APIs.

Agentic tools are available in the interactive CLI chat session: run `ragrails chat` with no query argument. This is separate from the stateless `rag.chat()` SDK method, which does not execute tools. The SDK exposes the lower-level tool-calling API, but your application owns tool execution and approval.

<Warning>`api_call` can make real HTTP requests. The interactive CLI validates tool calls first and asks for confirmation before side-effecting API calls.</Warning>

## Start the interactive chat

```bash CLI theme={null}
ragrails chat
```

Inside the REPL:

```text theme={null}
> /tools
> Look up the current docs page at https://example.com/docs and compare it to our stored answer.
> Call the staging API to create a test ticket with this payload: ...
```

## Why this is CLI-only today

`rag.chat()` is a stateless RAG turn: it retrieves context, calls the LLM, and returns a `ChatResult`. It does not own a user session, approval UI, authorization policy, request allowlist, or audit log.

The interactive CLI can safely provide built-in tools because it has a human in the loop. Before a side-effecting `api_call` runs, the CLI validates the arguments and asks the user to confirm the exact request.

For SDK apps, those decisions are application-specific. Use [Tool Calling](/capabilities/tool-calling) to build a tool loop where your app controls validation, permissions, confirmation, execution, and logging.

## Built-in tools

| Tool        | Confirmation | What it does                                                                              |
| ----------- | ------------ | ----------------------------------------------------------------------------------------- |
| `web_fetch` | No           | Fetches a URL and returns readable markdown text, trimmed to 8,000 characters.            |
| `api_call`  | Yes          | Makes a live HTTP request with explicit `method`, `url`, `headers`, `params`, and `body`. |

The `/tools` command lists registered tools, required fields, and confirmation policy.

## Tool safety model

1. The model proposes a provider-neutral tool call.
2. Ragrails validates required arguments and schema-specific rules.
3. Tools requiring confirmation pause for user approval.
4. Declined or invalid calls are not executed; the model receives a tool result explaining why.
5. The loop stops when the model returns final text or reaches the maximum tool iterations.

`api_call` validation requires:

| Requirement         | Detail                                                      |
| ------------------- | ----------------------------------------------------------- |
| Required keys       | `method`, `url`, `headers`, `params`, and `body`.           |
| Allowed methods     | `GET`, `POST`, `PUT`, `PATCH`, `DELETE`.                    |
| Body requirement    | `POST`, `PUT`, and `PATCH` require a non-empty `body`.      |
| Headers/params/body | Each must be an object. Use `{}` only when genuinely empty. |
| Authorization       | Placeholder values such as `<token>` are rejected.          |

## When agentic tools help

| Need                                                               | Tool        |
| ------------------------------------------------------------------ | ----------- |
| Check a live web page that was not indexed                         | `web_fetch` |
| Compare stored docs with a current external page                   | `web_fetch` |
| Fetch account details from an API after the user gives credentials | `api_call`  |
| Create or update a resource through an HTTP API                    | `api_call`  |

## Boundaries

| Boundary         | Current behavior                                                                                                            |
| ---------------- | --------------------------------------------------------------------------------------------------------------------------- |
| SDK `rag.chat()` | Does not call tools. Use [Tool Calling](/capabilities/tool-calling) and execute tools inside your own application boundary. |
| REST chat        | Does not expose the CLI agentic tool loop.                                                                                  |
| Tool set         | Built-in CLI tools are `web_fetch` and `api_call`.                                                                          |
| Iterations       | The tool loop stops after a bounded number of tool iterations.                                                              |
| Streaming        | Interactive chat can stream plain answers, but `chat_stream()` does not stream agentic tool execution.                      |

Reference: [CLI chat](/usage/cli/chat) and [Tool Calling](/capabilities/tool-calling).

## Related pages

* [Tool Calling](/capabilities/tool-calling)
* [Streaming](/capabilities/streaming)
* [CLI chat](/usage/cli/chat)
* [Chat](/features/chat)