Skip to main content
Glama
ClearStack Data MCP server

ClearStack Data MCP server

by Wordhalm

Search Google Ads Transparency Center

search_google_ads
Read-only

Retrieve a company's Google Search, Display, and YouTube ads from the Ads Transparency Center to research competitors, including formats, dates, URLs, and preview images.

Instructions

List the ads a company runs on Google (Search, Display, YouTube) from the public Google Ads Transparency Center: advertiser, format, first and last shown dates, ad URL and preview image. Use it for competitor research. Cost on the user's Apify account: $0.002 per call + $0.0012 per ad returned.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "targets": "<targets>"
    },
    "name": "search_google_ads"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoALL
regionNoISO-2 country code ("US", "GB", "FR") or "ALL".ALL
targetsYesAdvertiser domains ("stripe.com"), Google advertiser IDs ("AR1695…") or Transparency Center URLs.
dateRangeDaysNoOnly ads shown in the last N days; 0 = all history.
maxAdsPerTargetNo

Output Schema

NameRequiredDescriptionDefault
actorYesApify Actor that produced the data
itemsYes
runIdYesApify run ID; pass it to get_run_results if finished is false
statusYesApify run status, e.g. SUCCEEDED or RUNNING
finishedYesfalse when the run was still going and items are partial
itemCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious context: the data comes from a public transparency center and that cost is metered per call plus per ad returned. It omits pagination/truncation behavior and how the per-ad charge interacts with maxAdsPerTarget, keeping it below a 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 tight sentences, front-loaded with purpose, then use case, then cost — no filler. The enumeration of return fields is somewhat redundant given an output schema exists, which is the only minor waste.

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 annotations and an output schema already supplied, the description needs only to add source, cost, and intent — which it does. It is nearly complete for a read-only search tool; only truncation behavior and the cost-to-volume relationship are unaddressed.

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 coverage is 60%, and the description's field list (advertiser, format, dates, URL, preview) describes outputs rather than inputs, so it adds little meaning to targets, region, dateRangeDays, or maxAdsPerTarget. The per-ad pricing hint implicitly connects to result volume, but the input parameters themselves remain documented only by the schema.

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?

Names a specific verb (list), resource (ads), source (public Google Ads Transparency Center) and the surfaces covered (Search, Display, YouTube), plus the fields returned. An agent can tell instantly this is an ad-library lookup, distinct from the job-posting, Telegram, and company-verification siblings.

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?

"Use it for competitor research" gives one positive use case and the public data source implies the limits, but there is no statement of when NOT to use it, no prerequisites, and no explicit routing to alternatives. Usage is implied rather than specified.

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