Skip to main content
Glama
Google Workspace MCP connector

Google Workspace MCP connector

by animesh-ex

drive_search

Read-only

Search Google Drive files by name, full-text content, type, folder, or raw Drive query to find documents, spreadsheets, slides, PDFs, and folders.

Instructions

Search Google Drive files by name/full text, type, or folder. Optionally pass a raw Drive 'q' query.

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": "drive_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoSubstring of the file name
typeNoany
orderByNomodifiedTime desc
folderIdNoOnly files directly inside this folder
fullTextNoSearch inside file contents
pageSizeNo
rawQueryNoRaw Drive API query, overrides other filters
pageTokenNo
includeTrashedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds little beyond that: it does not mention pagination behavior, the default page size of 30, that trashed files are excluded by default, or that rawQuery silently overrides the other filters (that precedence note lives only in the schema).

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?

Two short sentences, front-loaded with the primary capability and finishing with the escape hatch. Nothing is padded, though the second sentence could state the override precedence rather than merely offering the option.

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?

For a 9-parameter read tool with no output schema and low schema description coverage, this is only adequate: it names the search dimensions but leaves result shape, pagination, defaults, and filter precedence to be inferred. An agent can call it, but may need the schema to call it well.

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 only 44%, so the description should carry more weight. It does map to name, fullText, type, folderId and rawQuery, but adds no syntax, format, or precedence detail for those, and it says nothing about orderBy, pageSize, pageToken, or includeTrashed.

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 gives a specific verb and resource ("Search Google Drive files") and enumerates the filterable dimensions: name, full text, type, folder, plus an optional raw 'q' query. That is enough for an agent to distinguish it from drive_get_file or drive_read_file_text, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: it is a search tool, and the second sentence hints that a raw Drive query is an option. There is no explicit guidance on when to prefer this over drive_list_folder, when to use rawQuery instead of structured filters, or what happens when zero filters are supplied.

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