Skip to main content
Glama

ADS Beast

chatgpt_ads_draft_generate

Builds intent clusters and ad texts within the platform limits from a business description and returns them for review. Nothing is published. Takes up to a minute. AI: 1 AI request.

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": {
      "business": "<business>"
    },
    "name": "chatgpt_ads_draft_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
geoNoWhere the ads should show.
urlNoLanding page.
businessYesWhat the business does, its offer and for whom.
clustersNoNumber of clusters, 1-8.
languageNoLanguage code, e.g. en.
client_idNo
ads_per_clusterNoAds per cluster, 1-5.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: no external publication side effects, an expected latency of up to a minute, and a cost signal of one AI request. That is meaningful operational context for a non-destructive but non-read-only tool that calls an external model. It still omits whether drafts persist and under which client_id they are stored.

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?

Four short sentences, front-loaded with what is produced and followed by the side-effect, latency and cost facts. No filler and nothing buried.

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?

Covers purpose, safety scope, latency and cost, which is most of what an agent needs for a seven-parameter generator. With no output schema, it could still say more about the shape of the returned clusters and ads, but it is close to complete.

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 86%, so the schema already explains geo, url, clusters, language and ads_per_cluster. The description adds that generation is bounded by 'platform limits', tying to the 1-8 and 1-5 ranges, but says nothing extra about the undocumented client_id parameter.

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

Purpose4/5

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

States a specific verb and artifact: builds intent clusters and ad texts from a business description, then returns them for review. The 'Nothing is published' clause separates it from publish/prepare siblings, though it never names an alternative such as prepare_chatgpt_ads_publish or chatgpt_ads_policy_check explicitly.

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

Usage Guidelines3/5

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

Workflow position is implied by 'returns them for review' and 'Nothing is published', which tells an agent this is a pre-publish drafting step. However, it gives no explicit guidance on when to prefer it over sibling generators like telegram_ads_draft_generate, creative_copy_generate, or campaign_strategy_generate, and no prerequisites are stated.

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.