Google Ads - AdLoop

Overview Schema Source Related Servers Discussions Admin

Ad performance

get_ad_performance

Read-only

Retrieve ad-level performance metrics including impressions, clicks, CTR, conversions, and cost. Enable compact mode to output top ads and headline counts for quicker audits.

Instructions

Get ad-level performance data including headlines, descriptions, and metrics.

Returns: ad type, headlines, descriptions, final URL, impressions, clicks, CTR, conversions, cost for each ad.

Set compact=true for audits/overviews: returns totals, the top-10 ads with headline/description COUNTS instead of full asset lists, plus incomplete-RSA and single-ad ad-group findings (~90% smaller).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`compact`	No
`customer_id`	No
`date_range_end`	No
`date_range_start`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.12.0Jul 12, 2026
- addedInput schema / properties / compact
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
First observedv0.9.0Jun 19, 2026

TDQS

A4.2/5.0

Behavior5/5

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

The description is consistent with readOnlyHint=true and describes only data retrieval with no side effects. It also discloses output-shaping behavior for compact mode, adding useful transparency beyond the annotations.

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?

The description is concise and front-loaded with the tool's purpose, followed by a short returns list and a compact-mode note. There is no redundant or misleading content.

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?

Core return fields and compact-mode behavior are covered well, and the annotations clarify read-only safety. It could provide more context around date-range and customer_id semantics, as well as explicit differentiation from sibling reporting tools, but it is generally sufficient.

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?

Only the compact parameter is explained in detail; customer_id, date_range_start, and date_range_end are left without format or constraint guidance. Parameter names provide basic meaning, but the schema description coverage is 0% and the description does not fill all gaps.

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?

The description clearly states that the tool retrieves ad-level performance data and enumerates the returned metrics. It is easy to distinguish from campaign, keyword, and asset reporting tools by title and content.

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?

The description provides some usage guidance by suggesting compact=true for audits/overviews, but it does not explicitly explain when to prefer this tool over sibling tools such as get_campaign_performance or get_keyword_performance. The intended use case must be inferred.

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

Deploy Server