Skip to main content
Glama

ChatGPT Ads: pause or resume

chatgpt_ads_set_status
DestructiveIdempotent

Pause or resume a ChatGPT Ads campaign, ad group or ad (its id starts cmpn_, adgrp_ or ad_). Call WITHOUT confirm first to see its current state and show it to the person, then call again with confirm: true. Resuming starts spending the client's money.

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": {
      "account": "<account>",
      "id": "<id>",
      "status": "<status>"
    },
    "name": "chatgpt_ads_set_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYescmpn_…, adgrp_… or ad_… from chatgpt_ads_list_campaigns or chatgpt_ads_report
statusYes
accountYesThe ChatGPT Ads account: its client's name, the account name, or its adacct_ id (chatgpt_ads_list_accounts)
confirmNoLeave false to preview: nothing changes and the preview shows exactly what would happen. Set true only after the user has agreed to this exact change.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered; the description adds genuinely new behavior: a no-op preview mode when confirm is false, and the real-world cost implication of resuming. It doesn't cover failure behavior for invalid or cross-account ids, which keeps it at 4.

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?

Three short sentences, front-loaded with the action and accepted id types, then the call protocol, then the risk warning in the final position where it lands hardest. No filler.

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?

With no output schema, the description usefully explains that the preview 'shows exactly what would happen' and that the first call returns current state. Enough to call correctly for a 4-parameter mutation tool; minor gaps around error cases remain.

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 coverage is 75% and the schema already documents id prefixes, account forms, status enum, and the confirm preview default. The description largely restates those semantics in prose (confirm two-call flow) rather than adding format or validation detail the schema lacks, so the baseline 3 applies.

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 pair ('pause or resume') and the exact resource set (campaign, ad group, ad), reinforced by the id prefixes cmpn_/adgrp_/ad_. An agent can immediately tell this is the ChatGPT Ads status-toggle tool rather than a budget, bidding, or Meta-ads sibling.

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 an explicit two-step protocol: first call without confirm to preview current state and show the user, then call again with confirm: true only after agreement. It also flags the consequence of resuming (spending client money). It does not name sibling alternatives (e.g., the budget tool) or state when not to use it, so it falls short of a full 5.

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.