ChatGPT Ads MCP server

openai ads get bulk job operations

openai_ads_get_bulk_job_operations

Read-onlyIdempotent

Read paginated Bulk API job outcomes—created, updated, validated, failed, or skipped—and page with after when has_more is true, so you can verify results without resubmitting an uncertain job.

Instructions

Read one page of Bulk API operation outcomes: created, updated, validated, failed or skipped. Pass the last operation_id as after only when has_more is true. A partial failure never rolls back earlier operations; do not resubmit an uncertain job.

Input Schema

Name	Required	Description
`jobId`	Yes	Native bulk job ID, blkmtnjob_ followed by its identifier, returned when the job was submitted.
`query`	No	Page size from 1 to 100 and, for later pages, the last operation_id of the previous page as after.
`adAccountId`	Yes	The adacct_ ID configured in OPENAI_ADS_ACCOUNT_ID. The API key is scoped to this one account; another ID is refused.

Output Schema

Name	Required	Description	Default
`result`	Yes	Original tool result: parsed JSON when the text is JSON, otherwise the text or multiple MCP content blocks. Provider fields depend on the selected query.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedOutput schema / properties / result / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "properties": {},
-    "type": "object"
-  },
-  {
-    "items": {},
-    "type": "array"
-  },
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "boolean"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "items": {},
+    "type": "array"
+  },
+  {
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  },
+  {
+    "type": "null"
+  }
+]

First observedv1.0.0Oct 23, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description instead adds semantics the annotations cannot: partial failures do not roll back earlier operations, paging is gated on has_more, and an uncertain job should not be resubmitted. That's substantive context beyond structured fields, though it doesn't address consistency/latency of the operation log.

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 tight sentences: what it returns, how to page, and how to interpret/handle failure. The paging contract is front-loaded right after the purpose, and no sentence is 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?

An output schema exists, so return-shape explanation is unnecessary, and the description covers the two things that matter for a paginated read of an async job: cursor gating and partial-failure semantics. It stops just short of stating where has_more lives or whether operations are available before the job finishes.

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 100%, so 3 would be the floor, but the description adds real meaning the schema lacks: the cursor must be the last operation_id and is only valid when has_more is true. That conditional is not present in the 'after' property definition, so the prose genuinely compensates.

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?

The description names a specific verb and resource ('Read one page of Bulk API operation outcomes') and even enumerates the outcome types (created, updated, validated, failed, skipped), which is far more than a restatement of the title. It doesn't explicitly contrast itself with the sibling openai_ads_get_bulk_job, so the boundary between 'job status' and 'job operation outcomes' must be inferred from naming.

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?

It gives one concrete operational rule — pass the last operation_id as after only when has_more is true — plus a caution not to resubmit an uncertain job. What's missing is when to reach for this tool versus openai_ads_get_bulk_job or openai_ads_get_mutation; usage is implied by the paging instruction rather than stated as a selection rule.

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

Deploy Server