Skip to main content
Glama

fetch_keyword_forecasts

Query real Google Ads Keyword Planner search volumes, competition, and top-of-page CPC bids using Upfixe's approved Google Ads Developer Token.

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": "fetch_keyword_forecasts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax keyword ideas to return (default: 100, max: 250).
seedsNoUp to 20 seed keywords to expand in Keyword Planner.
customerIdNo10-digit Google Ads customer ID (optional if set in your MCP token).
countryCodeNo2-letter ISO country code (default: 'US', e.g., 'GB', 'DE', 'CA').
languageCodeNo2-letter ISO language code (default: 'en').
landingPageUrlNoOptional landing page URL to extract keyword ideas from.
loginCustomerIdNoOptional 10-digit MCC Manager Customer ID if accessing a client account through an MCC.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / country
      Removed value: -{
      -  "description": "Target geography — any granularity Google Ads accepts: city, state, region, country, or postal code. Disambiguate non-unique names with the country (e.g. 'London, United Kingdom' not just 'London' — London, Ontario exists; 'Paris, France' not 'Paris' — Paris, Texas exists). For local-service brands push for city-level. Field name is 'country' for legacy reasons but free-text location resolves correctly via Google's geoTargetConstants:suggest API.",
      -  "type": "string"
      -}
    • addedInput schema / properties / countryCode
      Added value: +{
      +  "description": "2-letter ISO country code (default: 'US', e.g., 'GB', 'DE', 'CA').",
      +  "type": "string"
      +}
    • addedInput schema / properties / customerId
      Added value: +{
      +  "description": "10-digit Google Ads customer ID (optional if set in your MCP token).",
      +  "type": "string"
      +}
    • changedInput schema / properties / landingPageUrl / description
      Previous value: -"Optional landing-page URL. KP extracts page-relevant ideas and blends with seeds."New value: +"Optional landing page URL to extract keyword ideas from."
    • removedInput schema / properties / landingPageUrl / format
      Removed value: -"uri"
    • removedInput schema / properties / language
      Removed value: -{
      -  "description": "ISO-639-1 language code: en, fr, es, de, pt, it, etc.",
      -  "type": "string"
      -}
    • addedInput schema / properties / languageCode
      Added value: +{
      +  "description": "2-letter ISO language code (default: 'en').",
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Max keyword ideas to return (default: 100, max: 250).",
      +  "type": "number"
      +}
    • addedInput schema / properties / loginCustomerId
      Added value: +{
      +  "description": "Optional 10-digit MCC Manager Customer ID if accessing a client account through an MCC.",
      +  "type": "string"
      +}
    • changedInput schema / properties / seeds / description
      Previous value: -"0-20 seed keywords. Optional if landingPageUrl is provided."New value: +"Up to 20 seed keywords to expand in Keyword Planner."
    • removedInput schema / properties / seeds / items / minLength
      Removed value: -1
    • removedInput schema / properties / seeds / maxItems
      Removed value: -20
    • removedInput schema / required
      Removed value: -[
      -  "country",
      -  "language"
      -]
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose a genuinely important constraint — that it relies on Upfixe's approved Google Ads Developer Token — which signals an auth dependency, and 'real' implies live rather than cached data. However, it says nothing about rate limits, quota consumption, failure modes, or what happens if the token/customer ID is missing, which are material for a 7-parameter live-API call.

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?

A single front-loaded sentence with the resource and returned metrics up front and no wasted clauses. Slightly promotional phrasing ('real', 'Upfixe's approved') occupies space that could have carried usage or behavioral detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Seven optional parameters plus no output schema and no annotations means the description should do more than one sentence. It does name the returned metrics, partially compensating for the missing output schema, and the schema fully documents parameters. But context on quota/limits and when to prefer a different tool is absent, leaving it only minimally adequate for a live third-party API call.

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%, with every parameter (limit, seeds, customerId, countryCode, languageCode, landingPageUrl, loginCustomerId) documented with defaults and formats, so the baseline is 3. The description adds no parameter-level nuance beyond restating the output fields, so it neither helps nor hurts.

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

Purpose4/5

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

The description states a specific verb (Query) and resource (Google Ads Keyword Planner search volumes, competition, top-of-page CPC bids), so an agent knows exactly what data comes back. It does not name or contrast with any sibling, but the siblings listed (account listing, campaign publishing, status/budget updates) are far enough away that disambiguation is not urgent.

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?

There is no when-to-use versus when-not-to-use guidance, no statement of prerequisites beyond the token mention, and no hint about alternatives for keyword research. An agent must infer entirely from the tool name when this is the right call.

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