Skip to main content
Glama

google_api_search

Read-onlyIdempotent

Searches the Google API Discovery index for Workspace REST methods and returns method IDs plus parameters to invoke via google_api_call, including methods without dedicated tools.

Instructions

Search the Google API Discovery index for any Workspace REST method, including ones with no dedicated tool here. Returns method ids + parameters to invoke via google_api_call. APIs: gmail, drive, calendar, sheets, docs, slides, forms, people, searchconsole, tasks, chat, meet, driveactivity, drivelabels, admin_directory, admin_reports, admin_datatransfer, groupssettings, analyticsadmin, analyticsadmin_v1alpha, analyticsdata, appsmarket, classroom, cloudidentity, cloudsearch, groupsmigration, keep, licensing, postmaster, reseller, script, vault, workspaceevents.

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": {
      "query": "<query>"
    },
    "name": "google_api_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiNoRestrict the search to one API alias
queryYesKeywords, e.g. "slides create presentation" or "drive revisions"
maxResultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.4.1
    • addedInput schema / properties / api / maxLength
      Added value: +64
    • addedInput schema / properties / query / maxLength
      Added value: +500
  2. First observedv0.0.0-semantically-released

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and open-world. The description adds what annotations cannot: it returns method ids plus parameter metadata as a precursor to google_api_call. It omits ranking/pagination behavior of maxResults and whether results include full parameter schemas versus just names.

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?

Purpose and return shape are front-loaded in the first sentence, with the action handoff to google_api_call immediately after. The trailing 33-item API alias list is long and dominates the second half, though it is factually useful for the `api` parameter.

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?

With no output schema, the description carries the return-value burden and does so ('method ids + parameters'). Combined with the annotation-covered safety profile, the only meaningful gap is maxResults semantics and result-pagination behavior for a discovery search.

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 coverage is 67%: `query` and `api` are documented in the schema, while `maxResults` has no description anywhere. The description does add value by enumerating valid API alias values (gmail, drive, ... analyticsadmin_v1alpha), which makes the `api` filter concretely usable beyond the schema's 'Restrict the search to one API alias.'

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 ('Search the Google API Discovery index'), names the exact scope ('Workspace REST method'), and explicitly distinguishes itself from the per-service *_discover siblings by covering methods 'with no dedicated tool here.' The output ('method ids + parameters') is also named.

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?

Clear implied routing: use this when a dedicated discover tool doesn't exist, then invoke via google_api_call. It does not explicitly say to prefer drive_discover/gmail_discover first for those services, so the ordering against siblings is only implied by the schema's `api` filter and the 'no dedicated tool' phrase.

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