Skip to main content
Glama

Visibility Genies

Get a competitor's ads

get_competitor_ads

Collects the ads one advertiser (or a domain) ran on Google Search, YouTube, Shopping, Maps and Play, in the project's country, from Google's Ads Transparency Center: each ad's format, when it was first and last shown, and a preview URL. Queued at normal priority: a 'processing' answer means call again with the same arguments in 2-3 minutes, at no extra cost. Estimated price: $0.01 for 40 ads, billed per 40. Each call may spend up to the workspace's agent spend limit ($2.00 unless changed in Settings) without asking: it holds at most its estimate plus a margin while it runs and is charged what it bought, never more. A call whose maximum is above the limit is refused before anything is bought, with its estimate and maximum: ask the user, then call again with approvedMaxCostUsd set to the amount they approved.

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": {
      "projectId": "<projectId>"
    },
    "name": "get_competitor_ads"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoHow many ads to collect: 40, 80, 120. Defaults to 40. Billed per 40.
domainNoA domain whose advertisers' ads to collect, e.g. example.com.
platformNoWhere the ads ran. Defaults to all.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
advertiserIdNoAn advertiserId from find_ad_advertisers. Supply exactly one of advertiserId or domain.
approvedMaxCostUsdNoThe most, in USD, the user approved for this call after seeing its estimate and maximum. Only needed after a call was refused for costing more than the workspace's agent spend limit; never set it without asking the user.

Output Schema

NameRequiredDescriptionDefault
adsNo
costNo
metaNo
statusYes
savedResultIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) by disclosing normal-priority queuing, the meaning of a 'processing' response, the price ($0.01 per 40 ads, billed per 40), the workspace agent spend limit and hold margin, and the fact that refusal happens before any purchase. The charge-never-exceeds-estimate guarantee and the approvedMaxCostUsd escalation path are exactly the details an agent needs before spending money.

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 what is collected and from where, then cost and retry mechanics in a logical order. It is one dense paragraph with a long spend-limit sentence, which costs some scannability, but no sentence is filler.

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 paid, asynchronous, open-world collection tool, everything material is covered: cost model, spend ceiling, retry timing, identifier sourcing, and the approval loop. An output schema exists, so the absence of return-value detail is not a gap.

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%, so the baseline is 3, but the description adds real meaning for approvedMaxCostUsd — it exists only after a refusal, must be set to the amount the user actually approved, and must never be set without asking. The advertiserId/domain one-of rule and the per-40 billing of depth are reinforced rather than newly explained.

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 ('Collects the ads one advertiser (or a domain) ran') plus the exact source (Google's Ads Transparency Center) and the surfaces covered (Search, YouTube, Shopping, Maps, Play). The returned fields (format, first/last shown, preview URL) are named, so an agent can distinguish this from the competitor-refresh and link-change siblings without opening the 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 concrete operating guidance: supply exactly one of advertiserId or domain, find ids via find_ad_advertisers, and re-call with identical arguments in 2-3 minutes when the answer is 'processing'. It also explains the refusal path and the approvedMaxCostUsd follow-up. What it lacks is any explicit comparison or exclusion against sibling tools such as get_competitor_link_changes.

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.

Resources