Skip to main content
Glama

Delete a Meta ad set

ads_delete_ad_group
Destructive

Delete one Meta ad set from ads_get_tree, with its ads. Irreversible, and stops its delivery at once; the campaign stays. Confirm the ad set by name with the user first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "adGroupId": "<adGroupId>",
      "adAccountId": "<adAccountId>"
    },
    "name": "ads_delete_ad_group"
  }
}

Input Schema

NameRequiredDescriptionDefault
platformNometa_ads, tiktok_ads or linkedin_ads. Needed only when the profile has more than one ad network and no accountId is given.
accountIdNoThe Facebook accountId from list_accounts. Without it, pass profileId to use that profile's Facebook connection.
adGroupIdYesAn ad set id from ads_get_tree.
profileIdNoA profileId from list_profiles. Optional when accountId is given, which names its profile; if both are given they must agree.
adAccountIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true, but the description adds real behavioral detail beyond them: the deletion is irreversible, it cascades to the ad set's ads, delivery halts immediately, and the parent campaign is left intact. It also prescribes a user-confirmation step, which is exactly the kind of safety context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, no filler. The destructive scope and irreversibility are front-loaded, and the confirmation instruction lands last where it is acted on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter destructive tool with no output schema, the description covers the critical unknowns: what gets destroyed, what survives, and the confirmation workflow. Minor gaps remain around downstream effects on reporting/insights data and the expected response, but an agent has enough to call it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 80%, so accountId, profileId, and platform are already documented in the schema. The description only reinforces that the id comes from ads_get_tree; it adds nothing about the profile/account resolution or the platform fallback logic, leaving the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete one Meta ad set'), names the source of the identifier (ads_get_tree), and clarifies cascade scope ('with its ads'). This distinguishes it cleanly from siblings like ads_delete_ad and ads_delete_campaign.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear precondition (identify the ad set via ads_get_tree) and an operating instruction ('Confirm the ad set by name with the user first'), plus a consequence note that the campaign survives. It stops short of naming a non-destructive alternative such as ads_set_status for pausing instead of deleting, which would be the 5 mark.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources