brand_detach_advertiser
Remove the link between an ad account and a brand. The brand and its context stay.
Ask to remove the link between an ad account and a brand. The brand, its context and its files stay.
“Acme no longer uses that Meta ad account. Detach it.”
The agent calls brand_detach_advertiser. You then see the brand with no link to that ad account. An agent that works on the ad account no longer finds Acme.
The job guide Describe a brand shows each step of the job.
Reference
Detach an ad account from a brand. The brand itself and its context are untouched — only the link goes.
Input
| Argument | Type | Required | Description |
|---|---|---|---|
advertiser_id |
string | yes | The ad account id (acc_…). Discover ids with list_advertisers. |
brand_name |
string | yes | The brand slug. |
Output
A successful call returns this object in structuredContent.
| Field | Type | Always present | Description |
|---|---|---|---|
advertiserId |
string | yes | The ad account (acc_…). |
brandSlug |
string | yes | The slug of the brand. |
detached |
true |
yes | The link is removed. |
Failure codes
A failed call has isError set, and structuredContent.error holds one of these codes. Errors describes the shape of a failed call.
not_foundadvertiser_not_ownednot_attachedforbiddeninvalid_requestinternal_error
Scope
The token must hold brand:write. Auth & scopes 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:
{
"advertiser_id": "acc_1203456789012345",
"brand_name": "acme"
}
The result, in structuredContent:
{
"advertiserId": "acc_1203456789012345",
"brandSlug": "acme",
"detached": true
}