Skip to main content
Glama
Google Ads Transparency

Google Ads Transparency

list_ads

Retrieve an advertiser's ads from Google's ad library by domain, with format, run dates, days shown, and links; filter by region and duration to spot long-running campaigns.

Instructions

List the ads an advertiser runs, from the Google Ads Transparency Center (Google's ad library). Free, no API key.

Returns one row per ad: advertiser name and ID, format, first shown, last shown,
days shown and a link to the ad. It does NOT return the ad text (headline,
description); use get_ads_with_copy for that.

Args:
    domain: advertiser website, e.g. "nike.com".
    region: 2-letter country code where the ad was shown, e.g. "US", "GB", "DE". Empty = all countries.
    ad_format: "text", "image" or "video". Empty = all formats.
    max_ads: how many ads to fetch, 1-200 (40 per page from Google).
    min_days_shown: keep only ads shown on at least this many days. Use 30+ to find long-running ads.
    sort: "recent" (most recently shown first) or "longest" (most days shown first).

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": {
      "domain": "<domain>"
    },
    "name": "list_ads"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorecent
domainYes
regionNo
max_adsNo
ad_formatNo
min_days_shownNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and mostly discharges it: it discloses cost ('free, no API key'), the underlying page size ('40 per page from Google'), the hard cap ('1-200'), and the exact returned columns including the explicit omission of ad text. Only failure/empty-result behavior is unstated, which is minor for a read-only listing tool.

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 purpose and the key exclusion, then a clean arg list; every line earns its place except the enumeration of returned columns, which partly duplicates the existing output schema. Slight redundancy, but the ordering and readability are strong.

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 six-parameter read-only listing tool with an output schema present, the description covers purpose, source, cost, scope filters, sorting, sizing, and the sibling handoff. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate and it does: every one of the six parameters is explained with examples ('nike.com', 'US', 'GB'), value semantics for sort ('recent' vs 'longest'), the meaning of empty strings as 'all', and a recommended threshold for min_days_shown. This meaningfully exceeds the bare schema, which has no descriptions, no enums, and only defaults.

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 ('list the ads an advertiser runs') plus the exact data source (Google Ads Transparency Center), and explicitly positions itself against the sibling by declaring it does not return ad copy and naming get_ads_with_copy. An agent can distinguish the two tools without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-not ('does NOT return the ad text') paired with the alternative to use instead ('use get_ads_with_copy for that'), and adds a tactical hint ('use 30+ to find long-running ads'). The filter semantics ('Empty = all countries', 'Empty = all formats') tell the agent how to broaden scope as well as narrow it.

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

Deploy Server

Other Tools