Skip to main content
Glama

captapi

by io.github.CDCStream
OverviewDiscussionsAdmin

google_ad_library_company_ads

Google publishes spend and impression ranges only for election ads; commercial advertisers omit both. isActive is true when lastShown is within 7 UTC days. Costs 2 credits. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoClient-side sort: last_shown (recent activity first) or first_shown. Default is ATC order.
cacheNoSet true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh.
limitNoMax items to return (default 20, max 200). Flat 2 credits when results are returned; 0 credits when totalReturned is 0.
topicNoOnly "all" is supported (commercial ATC). Google publishes spend and impression ranges only for election ads; commercial advertisers omit both. isActive is true when lastShown is within 7 UTC days.
cursorNoPagination cursor from nextCursor.
regionNoAlias for country.
countryNoTwo-letter ISO country / region code (soft filter). Default US. Alias: region. Non-ISO codes are a definitive 400 INVALID_COUNTRY.
end_dateNoYYYY-MM-DD — keep creatives whose shown window overlaps this end.
advertiserYesAdvertiser name, domain (e.g. nike.com), or Google advertiser ID (AR…). Prefer AR… from advertiser-search.
start_dateNoYYYY-MM-DD — keep creatives whose shown window overlaps this start.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / country / description
      Previous value: -"Two-letter ISO country / region code (soft filter). Default US. Alias: region."New value: +"Two-letter ISO country / region code (soft filter). Default US. Alias: region. Non-ISO codes are a definitive 400 INVALID_COUNTRY."
  2. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh."
  3. Changed8 schema fields changed
    • changedInput schema / properties / advertiser / description
      Previous value: -"Advertiser name, domain (e.g. nike.com), or AR id."New value: +"Advertiser name, domain (e.g. nike.com), or Google advertiser ID (AR…). Prefer AR… from advertiser-search."
    • changedInput schema / properties / cache / description
      Previous value: -"Serve from 24h cache when available."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."
    • changedInput schema / properties / country / description
      Previous value: -"ISO country / region code. Default US."New value: +"Two-letter ISO country / region code (soft filter). Default US. Alias: region."
    • changedInput schema / properties / end_date / description
      Previous value: -"YYYY-MM-DD overlap filter end."New value: +"YYYY-MM-DD — keep creatives whose shown window overlaps this end."
    • changedInput schema / properties / limit / description
      Previous value: -"Max results per page (default 20, max 200)."New value: +"Max items to return (default 20, max 200). Flat 2 credits when results are returned; 0 credits when totalReturned is 0."
    • addedInput schema / properties / sort
      Added value: +{
+  "description": "Client-side sort: last_shown (recent activity first) or first_shown. Default is ATC order.",
+  "type": "string"
+}
    • changedInput schema / properties / start_date / description
      Previous value: -"YYYY-MM-DD overlap filter start."New value: +"YYYY-MM-DD — keep creatives whose shown window overlaps this start."
    • addedInput schema / properties / topic
      Added value: +{
+  "description": "Only \"all\" is supported (commercial ATC). Google publishes spend and impression ranges only for election ads; commercial advertisers omit both. isActive is true when lastShown is within 7 UTC days.",
+  "type": "string"
+}
  4. Changed8 schema fields changed
    • changedInput schema / properties / advertiser / description
      Previous value: -"Advertiser name, domain, or Google advertiser ID."New value: +"Advertiser name, domain (e.g. nike.com), or AR id."
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache. Default false — always fetch fresh data."New value: +"Serve from 24h cache when available."
    • changedInput schema / properties / country / description
      Previous value: -"ISO country code. Default US."New value: +"ISO country / region code. Default US."
    • addedInput schema / properties / cursor
      Added value: +{
+  "description": "Pagination cursor from nextCursor.",
+  "type": "string"
+}
    • addedInput schema / properties / end_date
      Added value: +{
+  "description": "YYYY-MM-DD overlap filter end.",
+  "type": "string"
+}
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return. Default 20, max 200. Billed per result."New value: +"Max results per page (default 20, max 200)."
    • addedInput schema / properties / region
      Added value: +{
+  "description": "Alias for country.",
+  "type": "string"
+}
    • addedInput schema / properties / start_date
      Added value: +{
+  "description": "YYYY-MM-DD overlap filter start.",
+  "type": "string"
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true)."New value: +"Set true to serve from the 24h response cache. Default false — always fetch fresh data."
  6. Changed1 schema field changed
    • addedInput schema / properties / cache
      Added value: +{
+  "description": "Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true).",
+  "type": "boolean"
+}
  7. Added

TDQS

A3.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden — and it excels. It explicitly discloses credit costs (2 credits), the no-charge policy for empty results and failures, caching behavior (cache=true for a free 24h hit, default fresh), the spend/impression data-availability limitation, and precise isActive semantics (lastShown within 7 UTC days). This is rich behavioral context beyond what annotations would supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences with zero filler, front-loaded with the most decision-relevant caveat (spend/impressions only for election ads). Every sentence earns its place: field semantics, credit cost, charge exemption, and caching behavior are each covered in minimal words. The credit cost is conveyed in seven words.

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?

For a complex tool with 10 parameters, no output schema, and no annotations, the description covers the critical behavioral ground: costs, cache, data availability, and isActive meaning. Remaining gaps are an explicit statement of what the tool returns and routing against siblings, but the extraordinarily detailed schema compensates for much of that, leaving the definition nearly complete.

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%, so the baseline is 3. The tool description adds no parameter-level meaning itself, but it doesn't need to — the schema already documents every parameter in detail, including the country soft filter, the 400 INVALID_COUNTRY failure mode, the 'all'-only topic constraint, and the region/country alias. The schema does the heavy lifting here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description never explicitly states the core function — listing a company's ads from the Google Ad Library. It opens with data-availability caveats (spend/impressions only for election ads) and behavioral notes (isActive, credits, cache), so an agent must infer the verb+resource from the tool name and schema. The resource is identifiable, but the primary purpose is implied rather than stated, making it vague for a 10-parameter tool.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. The sibling list includes google_ad_library_ad_details, google_ad_library_advertiser_search, and facebook_ad_library_company_ads, and the description never distinguishes this tool from them or states conditions for choosing it. The closest hint is the schema's 'Prefer AR… from advertiser-search' in the advertiser parameter, but the tool-level description itself gives no routing or exclusion guidance.

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

All captapi toolsInspect
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.

Resources