---
title: document_delete
description: Delete a file of a brand, and its stored bytes.
---

Ask to remove a file from a brand. The agent deletes the file and its bytes.

> "Delete the old brand book from Acme."

The agent finds the file with [`document_list`](/mcp/tools/document-list), and then calls `document_delete`. Your client can ask you to confirm first. You then see Acme with no such file.

The job guide [Describe a brand](/mcp/tools/describe-a-brand) shows each step of the job.

## Reference

Delete a file attached to a brand, along with the stored bytes. The URL stops resolving immediately.

### Input

| Argument | Type | Required | Description |
| --- | --- | --- | --- |
| `document_id` | string | yes | The id of the document to delete. |

### Output

A successful call returns this object in `structuredContent`.

| Field | Type | Always present | Description |
| --- | --- | --- | --- |
| `deleted` | `true` | yes | The document is deleted. |
| `documentId` | string | yes | The id of the deleted document. |

### Failure codes

A failed call has `isError` set, and `structuredContent.error` holds one of these codes. [Errors](/mcp/errors) describes the shape of a failed call.

- `not_found`
- `forbidden`
- `invalid_request`
- `internal_error`

### Scope

The token must hold `brand:write`. [Auth & scopes](/mcp/auth) lists each scope.

### Annotations

A client reads these hints. A hint that the tool does not declare has the default value of the MCP specification.

- **Writes.** The tool can change data.
- **Destructive.** The tool can make a change that you cannot undo. A client can ask you to confirm before it calls the tool.
- **Not idempotent.** A second call with the same arguments can change more.
- **Closed world.** The tool reads and writes the data of AdCrunch only.

### Example

The arguments:

```json
{
  "document_id": "doc_5e2b41"
}
```

The result, in `structuredContent`:

```json
{
  "deleted": true,
  "documentId": "doc_5e2b41"
}
```