Skip to main content
Glama

Visibility Genies

Research keywords

research_keywords

Ideas from seeds: finds related keyword ideas with search volume, difficulty and CPC for 1-5 seed keywords in one call. For metrics on keywords you already have, use get_keyword_metrics. Estimated price per seed: ~$0.06 to $0.18 at 150 results, ~$0.10 to $0.29 at 300, ~$0.15 to $0.44 at 500 (Auto buys one to three sources), doubled with clickstream; ~$0.18 at any limit for countries served from Google Ads data, where difficulty/intent are unavailable. Asking again within 24 hours is answered from the saved copy at no charge: in Google Ads countries at any result limit, elsewhere for the same result limit and clickstream setting. Returns per-seed results, each with a link that reopens it in Keyword Research; a single bad seed won't fail the batch. 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>",
      "seeds": "<seeds>"
    },
    "name": "research_keywords"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedsYes1-5 seed keywords. Each seed is researched independently and returns related keywords with volume/difficulty/CPC. Bulk-friendly: prefer this over multiple single-seed calls.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
resultLimitNoMax keywords returned per seed. Defaults to 150.
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.
includeClickstreamDataNoRefine search volumes with clickstream data, which disaggregates Google Ads' grouped close-variant volumes (plurals/misspellings). DOUBLES the price of each seed. Default false (standard Google-Ads-derived volumes). No effect for countries served from Google Ads data.

Output Schema

NameRequiredDescriptionDefault
costNo
metaNo
resultsYes
savedResultIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description adds the material behavior an agent can't infer — per-seed pricing tiers, that the call spends up to the workspace agent spend limit without asking, that only the actual purchase is charged, and that one bad seed won't fail the batch. The refusal-then-approve flow and the 24-hour cache are exactly the kind of side effects that matter for a money-spending call.

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

Conciseness3/5

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

Purpose and the sibling hand-off are correctly front-loaded, but the middle is a dense block of price arithmetic and caveats, some of it restating schema text (clickstream doubling, the Google Ads-country limitation appears in both locationCode and includeClickstreamData). The parenthetical "(Auto buys one to three sources)" and repeated limit qualifiers add length an agent doesn't strictly need to select or invoke the tool.

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, multi-seed, open-world call with an output schema, the description covers what an agent must know: cost bounds, spend-limit refusal, caching, partial-failure tolerance, per-seed result shape with a reopen link, and country-level feature gaps. Return values are left to the output schema, which is correct.

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?

With 100% schema coverage the baseline is 3, and the description genuinely adds meaning: it ties resultLimit to price tiers ($0.06–0.18 at 150, up to $0.44 at 500) and flags that clickstream doubles the cost, which the schema states but without the price context. It also explains approvedMaxCostUsd's origin (post-refusal, user-approved amount) beyond the schema's "only needed after a call was refused".

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?

"Ideas from seeds: finds related keyword ideas with search volume, difficulty and CPC for 1-5 seed keywords in one call" states a specific verb, resource, output fields and input cardinality. It also names the sibling that handles the adjacent job ("For metrics on keywords you already have, use get_keyword_metrics"), so the 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?

It explicitly routes the alternative case to get_keyword_metrics and covers the re-run case ("Asking again within 24 hours is answered from the saved copy at no charge") with the exact conditions where that holds. The cost-approval escalation is spelled out as a concrete procedure: refusal before purchase, then re-call with approvedMaxCostUsd after asking the user.

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