> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/management-api/tools.md).

# Tools

Manage AI tools and tool scopes via the Management API.

Tools represent functions that AI agents can call during execution. They are registered by add-ons such as Agent and are organized into scopes that define their capabilities and permissions.

You can use the tool endpoints to list all user-configurable tools and their scopes, which is useful for building custom UIs or inspecting available agent capabilities.

## Available Endpoints

| Method | Endpoint                                     | Description                                       |
| ------ | -------------------------------------------- | ------------------------------------------------- |
| GET    | `/umbraco/ai/management/api/v1/tools`        | List all user-configurable tools grouped by scope |
| GET    | `/umbraco/ai/management/api/v1/tools/scopes` | List all tool scopes                              |

## Tool Model

{% code title="Tool Response" %}

```json
{
    "id": "get-content-by-id",
    "name": "Get Content By Id",
    "description": "Retrieves a content item by its unique identifier.",
    "scopeId": "content-read",
    "isDestructive": false,
    "tags": ["content", "read"]
}
```

{% endcode %}

### Properties

| Property        | Type      | Description                                      |
| --------------- | --------- | ------------------------------------------------ |
| `id`            | string    | Unique identifier for the tool                   |
| `name`          | string    | Display name                                     |
| `description`   | string    | Description of what the tool does                |
| `scopeId`       | string    | The scope this tool belongs to                   |
| `isDestructive` | boolean   | Whether the tool performs destructive operations |
| `tags`          | string\[] | Tags for categorization                          |

## Tool Scope Model

{% code title="Tool Scope Response" %}

```json
{
    "id": "content-read",
    "icon": "icon-document",
    "isDestructive": false,
    "domain": "content",
    "forEntityTypes": ["document"]
}
```

{% endcode %}

### Properties

| Property         | Type      | Description                                  |
| ---------------- | --------- | -------------------------------------------- |
| `id`             | string    | Unique identifier for the scope              |
| `icon`           | string    | Icon identifier for the backoffice UI        |
| `isDestructive`  | boolean   | Whether the scope contains destructive tools |
| `domain`         | string    | The functional domain of the scope           |
| `forEntityTypes` | string\[] | Entity types this scope applies to           |

## In This Section

{% content-ref url="/pages/qasLEKtakj3zK9Z91nbu" %}
[List Tools](/ai-in-umbraco/management-api/tools/list.md)
{% endcontent-ref %}

{% content-ref url="/pages/Hb56kDnyKPqySIeotHJr" %}
[List Tool Scopes](/ai-in-umbraco/management-api/tools/scopes.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/management-api/tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.