OpenAI Ads MCP

manage_conversions

Read-onlyIdempotent

Manage conversion pixels, API keys, event settings, and conversion reporting.

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": {
      "action": "<action>"
    },
    "name": "manage_conversions"
  }
}

Input Schema

Name	Required	Default
`name`	No
`after`	No
`limit`	No
`order`	No	desc
`action`	Yes
`before`	No
`entity_ids`	No
`event_type`	No
`source_ids`	No
`client_type`	No	web
`time_ranges`	No
`aggregation_level`	No
`custom_event_name`	No
`attribution_window_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedJul 28, 2026

TDQS

D1.8/5.0

Behavior1/5

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

The description uses 'manage' which implies write operations, but annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. This is a clear contradiction since the schema includes create and set actions, which are mutations. The description misleads about the tool's behavior.

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

Conciseness2/5

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

The description is a single short sentence, but it lacks important structural elements. It does not front-load the key action parameter or state that this is a multi-action tool. Being concise is not helpful if it omits critical information.

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

Completeness1/5

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

Given the tool's complexity (14 parameters, multiple actions, no output schema), the description is grossly incomplete. It fails to explain any action behaviors, parameter dependencies, or return values.

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

Parameters1/5

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

With 0% schema description coverage, the description should explain key parameters. It does not mention any of the 14 parameters, including the required 'action' parameter or how it affects behavior. No value is added beyond the schema structure.

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

Purpose3/5

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

The description states the verb 'manage' and lists several conversion-related resources (pixels, API keys, event settings, reporting), but it does not clarify that the tool performs different actions based on the 'action' parameter. It is clear enough to indicate the broad domain but lacks specificity.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus sibling tools like get_insights, get_account, etc. No context about when to choose manage_conversions over other tools is given.

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

All OpenAI Ads MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.