Skip to main content
Glama

ChatGPT Ads: change a campaign budget

chatgpt_ads_set_budget
DestructiveIdempotent

Change a ChatGPT Ads campaign's daily or lifetime budget, in real currency (50 means $50.00). Call without confirm first to see the current budget and the size of the change, show that to the person, then confirm: true. Raising a daily budget by more than 50% in one step needs acknowledge_large_change.

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>",
      "campaign_id": "<campaign_id>"
    },
    "name": "chatgpt_ads_set_budget"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
campaign_idYescmpn_… from chatgpt_ads_list_campaigns
daily_budgetNo
lifetime_budgetNo
acknowledge_large_changeNoRequired to raise a budget by more than 50% in one step.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, so the safety profile is known; the description adds genuine context on top: preview mode changes nothing, the confirmation gate is user-driven, and large increases require an extra acknowledgement flag. It does not cover failure modes (e.g. a rejected or out-of-policy budget) or how daily and lifetime budgets interact, which keeps it from a 5.

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 sentences, front-loaded with the verb and resource, then the call sequence. Every clause carries actionable information: units, the preview step, the confirm flag, and the large-change threshold. No filler or restatement of the title.

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

Completeness3/5

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

The mutation workflow is well covered, but the schema marks only account and campaign_id as required, leaving both budget fields optional; the description never says whether at least one budget must be supplied, what happens if both are given, or what the preview response contains. With no output schema, that leaves the agent guessing at the edge cases of a destructive operation.

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

Parameters4/5

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

Schema coverage is 67% and the two budget fields carry no schema description at all, so the description's currency explanation ("50 means $50.00") is the only place the numeric units are defined. The confirm/acknowledge_large_change semantics largely duplicate schema text, so the added meaning is real but concentrated in the budget params.

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 ("Change a ChatGPT Ads campaign's daily or lifetime budget") and pins down the unit convention ("50 means $50.00"). The platform scoping plus the daily/lifetime distinction separates it from the meta_* and ads_* budget siblings without the agent needing to open a schema.

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 operating procedure: call without confirm to preview, show the current budget and delta to the person, then set confirm: true. It also states the condition that triggers acknowledge_large_change (>50% daily increase). It stops short of naming when a sibling budget tool (meta_set_campaign_budget, ads_set_campaign_budget) is the right call instead, so not a 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.