Skip to main content
Glama

ChatGPT Ads: set up conversion tracking

chatgpt_ads_conversion_setup

Set up ChatGPT Ads conversion tracking for a client: uses the account's web pixel (or creates one) and the conversion event to count (leads by default), then says how to put it on the site. Call without confirm to see what exists and what would be created; confirm: true creates what's missing. Then install with gtm_install_tracking (openai_pixel_id + openai_event_path) or, without Tag Manager, give the person the snippet it returns. Its conversion_event_setting_id lets chatgpt_ads_build_campaign optimise for conversions.

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>"
    },
    "name": "chatgpt_ads_conversion_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
eventNolead_created
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

A4.4/5.0
Behavior4/5

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

Annotations already declare the write/exploratory profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds real context on top: the pixel is reused when present and only created when missing, and the default call is a no-op preview. It stops short of stating permission requirements, auth/account-access needs, or what happens on re-runs with conflicting settings, so a 4 rather than 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.

Conciseness4/5

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

Tight and front-loaded: purpose first, then the preview/confirm contract, then installation and the downstream link. It is dense but every clause conveys actionable routing information; only the final sentence is arguably optional padding for an agent that already knows the campaign builder.

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

Completeness5/5

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

There is no output schema, and the description compensates by naming the meaningful returns: the tracking snippet and conversion_event_setting_id. Given three parameters and a simple preview/create flow, an agent has enough to decide when to call it, how to call it safely, and what to do with the result.

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 67% with two of three parameters already described in the schema, so the baseline is 3. The description reinforces the confirm semantics ('creates what's missing' vs. see what exists) and notes that event defaults to leads, but adds no new syntax or accepted-value detail beyond the enum and descriptions already present.

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?

Opens with a specific verb plus resource ('Set up ChatGPT Ads conversion tracking for a client') and immediately names the two underlying objects it manipulates: the account's web pixel (reused or created) and the conversion event to count. It also states the tool's secondary output (site-install instructions), which lets an agent distinguish it from siblings like gtm_install_tracking or ads_create_conversion_action.

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

Usage Guidelines5/5

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

Explicitly prescribes the workflow: call without confirm to preview, set confirm: true only to create what's missing, then install via gtm_install_tracking (openai_pixel_id + openai_event_path) or hand the returned snippet to the user when there's no Tag Manager. It also names the handoff into chatgpt_ads_build_campaign via conversion_event_setting_id, so both the next step and the alternatives are covered.

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.