AdLoop

Analytics setup audit

audit_ga4_property

Read-only

Audit a GA4 property's setup in one call: the settings that quietly cost data or conversions.

Checks data retention (two months is GA4's default and cuts explorations short), the Google Ads link (and whether the configured Ads account is linked), each data stream's activity in the last 7 days, key events that never fired in 28 days or no key events at all, enhanced measurement per web stream, Google signals (and the thresholding they cause), the custom dimension and metric limits, and a property in the trash. Returns checks with status warn, info or ok (warnings first), a summary count, and the warnings as insights[]; a check the user may not read is listed under unavailable. Reads GA4 only (Admin API, part v1alpha, and two small Data API reports); for whether Google Ads imports the key events, run check_key_event_imports.

Google Analytics Data API: https://developers.google.com/analytics/devguides/reporting/data/v1 and Admin API: https://developers.google.com/analytics/devguides/config/admin/v1

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_ga4_property"
  }
}

Input Schema

Name	Required	Description	Default
`property_id`	No	GA4 property as "properties/123456789" or the bare numeric ID. If empty, uses the default from config.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations it discloses the exact APIs touched (Admin API, part v1alpha, two small Data API reports), a permission behavior most tools omit ('a check the user may not read is listed under unavailable'), and the result ordering (warnings first, then info, then ok). This is behavior an agent cannot infer from the annotation block.

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?

The purpose sentence is front-loaded and the check list is dense rather than padded. It runs long, and the trailing developer-documentation URLs plus some parenthetical asides could be trimmed without losing meaning, but nothing is genuinely redundant.

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?

For a single-parameter, read-only audit the description covers scope, data sources, result shape, warning ordering, and the permission-degradation path. With an output schema present it did not need to describe return values, yet the status/insights/unavailable summary it gives still helps an agent interpret results correctly.

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% and the single property_id parameter already documents the 'properties/123456789' vs bare numeric form and the empty-string default fallback. The description adds nothing further about the parameter, so the schema earns the credit and a baseline 3 applies.

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 opens with a specific verb and resource ('Audit a GA4 property's setup') and then enumerates exactly which settings are inspected: data retention, the Google Ads link, stream activity, unfired key events, enhanced measurement, Google signals, custom definition limits, and trashed properties. That level of enumeration distinguishes it cleanly from get_ga4_property and the drafting siblings.

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?

It gives a concrete routing rule to an alternative: for whether Google Ads imports the key events, run check_key_event_imports instead. It also frames the intended use ('in one call', settings that cost data or conversions). What it lacks is an explicit when-not statement for the other audit-adjacent siblings such as audit_event_coverage or health_check.

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

All AdLoop 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.