Skip to main content
Glama

Visibility Genies

Get autocomplete ideas

get_keyword_autocomplete

Buys Google Autocomplete for one keyword: the searches Google suggests as someone types it, in Google's order, long tail ideas in searchers' own words. Estimated price $0.01 per keyword, one request. Bought in the last 24 hours is read free, and every purchase opens free on Keyword Research's Autocomplete view; get_saved_keyword_autocomplete reads it without buying. Suggestions carry no volume: research_keywords or get_keyword_metrics price that. 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>",
      "keyword": "<keyword>"
    },
    "name": "get_keyword_autocomplete"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordYesThe keyword typed into Google, e.g. 'ski boots'.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
languageCodeNoLanguage code such as en, es or vi. When left out, the language of the project's default market is used (see list_projects).
locationCodeNoMarket location code, for example 2840 for the United States. When left out, the project's default market is used (shown by list_projects and changed in project settings). A few countries, Iceland (2352) among them, only have Google Ads data: search volume, CPC and trends are available there, but keyword difficulty, search intent and domain analytics are not.
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
costNo
metaNo
boughtYes
keywordYes
savedAtYes
suggestionsYes
savedResultIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With readOnlyHint=false already signalling a spend, the description adds substantive detail the annotations cannot: ~$0.01 per keyword, 24-hour cache reads are free, the workspace agent spend limit ($2.00 default), the hold-while-running model with 'charged what it bought, never more', and pre-purchase refusal. It is careful not to contradict destructiveHint=false/openWorldHint=true. A 5 is withheld only because the hold/margin mechanics are stated in a slightly circular way.

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 the purchase and what is bought, then pricing, then spend-limit mechanics — a sensible priority order. Dense but mostly earning its place; the spend-limit sentences are somewhat repetitive ('holds at most its estimate plus a margin while it runs and is charged what it bought, never more') and could be tightened.

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, open-world lookup with an output schema, the definition covers everything an agent needs: cost model, caching, spend cap, refusal handling, and pointers to the siblings that cover the missing volume dimension. Return values need not be explained since an output schema exists.

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 all five parameters are already documented, including the spend-limit and locationCode caveats; baseline is 3. The description reinforces approvedMaxCostUsd's workflow (only after a refusal, never without asking) and the 'one keyword per request' scoping of keyword, but adds no syntax or format detail beyond what the schema states.

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: 'Buys Google Autocomplete for one keyword', then clarifies the returned content (Google's suggested searches, in Google's order, long tail phrasing). It explicitly distinguishes itself from the saved-data sibling get_saved_keyword_autocomplete, so an agent can route 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?

Names alternatives with conditions: get_saved_keyword_autocomplete reads results 'without buying', and research_keywords or get_keyword_metrics supply the volume these suggestions lack. It also gives the exact recovery procedure when a call is refused for exceeding the spend limit — ask the user, then retry with approvedMaxCostUsd.

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