PingAura

Get ChatGPT Ads ad-group insights

get-openai-ads-ad-group-insights

Read-only

Get spend, impressions, clicks, CTR, CPC and CPM for one ChatGPT Ads ad group over a date range, as {data, has_more}. Defaults to one rollup row; aggregation_level ad gives a row per ad. ad_group_id comes from list-openai-ads-ad-groups. Set include_sales for order sales, ROAS, CPA and post-click conversion rate under the given attribution windows.

Input Schema

Name	Required	Description
`sort`	No	Sort directives, an array of {field, direction}. Example: [{"field":"spend","direction":"desc"}].
`limit`	No	Max rows
`since`	Yes	Range start date (YYYY-MM-DD, inclusive)
`until`	Yes	Range end date (YYYY-MM-DD, inclusive)
`domain_id`	Yes	Domain ID from list-domains
`time_basis`	No	Whether results are dated by ad_event_time or conversion_time. Defaults to ad_event_time. Applied only when include_sales is true.
`ad_group_id`	Yes	Ad group ID from list-openai-ads-ad-groups
`include_sales`	No	Also return conversions, CPA, post-click conversion rate, order sales and ROAS. Defaults to false.
`time_granularity`	No	Time granularity. Defaults to none (single rollup row).
`view_window_days`	No	View-through attribution window in days: 0 (off) or 1. Defaults to 1. Applied only when include_sales is true.
`aggregation_level`	No	Row grain: ad_account, campaign, ad_group or ad. Defaults to ad_group, one row for the whole scope.
`click_window_days`	No	Click attribution window in days: 7, 14 or 30. Defaults to 30. Applied only when include_sales is true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 31, 2026

changedInput schema / properties / click_window_days / description

Previous value: -"Click attribution window in days: 7, 14 or 30. Defaults to 30."New value: +"Click attribution window in days: 7, 14 or 30. Defaults to 30. Applied only when include_sales is true."

changedInput schema / properties / time_basis / description

Previous value: -"Whether results are dated by ad_event_time or conversion_time. Defaults to ad_event_time."New value: +"Whether results are dated by ad_event_time or conversion_time. Defaults to ad_event_time. Applied only when include_sales is true."

changedInput schema / properties / view_window_days / description

Previous value: -"View-through attribution window in days: 0 (off) or 1. Defaults to 1."New value: +"View-through attribution window in days: 0 (off) or 1. Defaults to 1. Applied only when include_sales is true."

Changed3 schema fields changedOct 30, 2026

changedInput schema / properties / ad_group_id / description

Previous value: -"Ad group ID"New value: +"Ad group ID from list-openai-ads-ad-groups"

changedInput schema / properties / domain_id / description

Previous value: -"Domain ID"New value: +"Domain ID from list-domains"

changedInput schema / properties / limit / description

Previous value: -"Max rows to return"New value: +"Max rows"

Changed3 schema fields changedOct 30, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / domain_id / pattern

Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"

removedInput schema / properties / sort / items / additionalProperties
```
Removed value: -false
```

Changed8 schema fields changedOct 29, 2026

addedInput schema / properties / click_window_days

Added value: +{
+  "description": "Click attribution window in days: 7, 14 or 30. Defaults to 30.",
+  "enum": [
+    7,
+    14,
+    30
+  ],
+  "type": "number"
+}

addedInput schema / properties / include_sales

Added value: +{
+  "description": "Also return conversions, CPA, post-click conversion rate, order sales and ROAS. Defaults to false.",
+  "type": "boolean"
+}

changedInput schema / properties / sort / items / properties / field / description

Previous value: -"Metric name, e.g. \"spend\", \"clicks\", \"impressions\", \"ctr\", \"cpc\", \"cpm\"."New value: +"Metric to sort by: spend, impressions, clicks, ctr, cpc or cpm. Sales figures, conversions included, cannot be sorted on."

addedInput schema / properties / sort / items / properties / field / enum

Added value: +[
+  "spend",
+  "impressions",
+  "clicks",
+  "ctr",
+  "cpc",
+  "cpm"
+]

removedInput schema / properties / sort / items / properties / field / minLength
```
Removed value: -1
```
addedInput schema / properties / sort / maxItems
```
Added value: +5
```

addedInput schema / properties / time_basis

Added value: +{
+  "description": "Whether results are dated by ad_event_time or conversion_time. Defaults to ad_event_time.",
+  "enum": [
+    "ad_event_time",
+    "conversion_time"
+  ],
+  "type": "string"
+}

addedInput schema / properties / view_window_days

Added value: +{
+  "description": "View-through attribution window in days: 0 (off) or 1. Defaults to 1.",
+  "enum": [
+    0,
+    1
+  ],
+  "type": "number"
+}

First observedOct 24, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already cover the read-only/no-destructive profile, and the description adds real value on top: the response shape {data, has_more}, the rollup-vs-granular default, and that attribution windows only apply when include_sales is true. It does not cover pagination mechanics or rate/limit behavior, keeping it at 4 rather than 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?

Three dense sentences, front-loaded with the metric list and return shape before getting into defaults and the include_sales switch. No filler, though the final sentence mildly duplicates what include_sales already spells out in the schema.

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?

With 12 parameters, no output schema, and conditional sales/attribution behavior, the description supplies the important bits: return envelope, default grain, and the include_sales gate. Sorting and limit/pagination behavior are left entirely to the schema, a minor gap given there is no output schema.

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 description coverage is 100%, so the baseline is 3. The description restates values the schema already documents (aggregation_level grain, include_sales contents, which metrics are returned) and does not add syntax, formatting, or interaction detail beyond that.

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 resource: fetch spend/impressions/clicks/CTR/CPC/CPM metrics for one ChatGPT Ads ad group over a date range, plus the return envelope {data, has_more}. Scope ('one ad group') implicitly distinguishes it from the account/campaign/ad insights siblings, but the description never names those alternatives explicitly.

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?

Clear operational context: ad_group_id comes from list-openai-ads-ad-groups, the tool defaults to one rollup row, and aggregation_level=ad yields a row per ad. It also explains when to set include_sales. No explicit when-not-use or alternative-tool routing, so it stops short of 5.

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

All PingAura 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.

Resources

Need Help?