Skip to main content
Glama

Google Ads: free waste scan across every account

ads_waste_scan

The free Google Ads waste scan: every Google Ads account this agency's Google logins reach (manager accounts' clients included, up to 15 with spend), no client needed. Returns how much of the last 30 days' spend was wasted, per account: searches that never converted and are plainly not buyers (jobs, DIY, plans) or spent more than a lead costs that account (judged only with 3+ conversions), minus ones an existing negative already blocks, plus Display inside Search campaigns. Other searches that didn't convert are not counted. Also per account, with each account's fixes: wasted searches, Display, clicks from outside the area, disapproved ads, Google's auto-applied recommendations, and broken conversion tracking (an account whose tracking recorded nothing is flagged, not counted). Starts a scan when none exists or refresh is true; a scan takes 1-3 minutes, so if it says running, tell the person and check again shortly. Reads only; changes nothing in Google Ads.

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": "ads_waste_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
refreshNoRun a new scan even if one finished in the last hour

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the 1-3 minute scan duration, the 'running' state and how to handle it, that tracking-less accounts are flagged rather than counted, and that the tool reads only and changes nothing in Google Ads. The 'Reads only' phrasing sits alongside readOnlyHint=false, but the description explains this itself — the tool kicks off a background scan job — so the two are reconcilable rather than contradictory.

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?

Front-loaded with the core promise (free waste scan, every account) before the waste definition and lifecycle details. It is a single dense paragraph with a couple of run-on clauses, but nearly every clause carries decision-relevant information, so the length is mostly earned.

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?

With no output schema, the description takes on the return-value burden and does so thoroughly: per-account wasted spend plus a per-account fix list (wasted searches, Display, out-of-area clicks, disapproved ads, auto-applied recommendations, broken tracking). Scan lifecycle, cardinality limits, and side-effect scope are all covered, leaving nothing an agent needs in order to call it correctly.

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% for the single parameter, so the baseline is 3; the description adds real meaning by explaining the default caching rule (a scan is reused if one finished in the last hour) against which refresh=true triggers a new run. That behavior is not derivable from the schema's own wording alone.

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?

States a specific verb and resource — a free waste scan across every Google Ads account the agency's logins reach — and defines what 'waste' means (non-buyer searches, over-CPL searches with 3+ conversions, Display inside Search, minus existing negatives). It also delimits what is NOT counted, so an agent can distinguish it from a generic report or diagnose tool without opening a schema.

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?

Gives clear entry conditions: no client needed, runs across all reachable accounts (up to 15 with spend, manager-account clients included), and starts a scan only when none exists or refresh is true. It omits explicit routing to sibling alternatives (e.g. ads_diagnose or ads_report) for agents who want a narrower or non-scanning view, so the when-not guidance is only partial.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.