Skip to main content
Glama

drive_search_files

Read-only

Search Google Drive and shared drives for files by name words, type, or folder; results return newest first and include IDs for attaching files to Classroom items.

Instructions

Find files in the teacher's Google Drive (including shared drives) by words in the name, by type or inside a folder, newest first. Use the returned id as a driveFile attachment. Returns one page as {items, nextPageToken}; continue until nextPageToken is null.

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_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoany
queryNoWords that appear in the file name, e.g. "práctica 05"
folderIdNoOnly files directly inside this Drive folder
fullDataNo
pageSizeNo
pageTokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.1.0

TDQS

A4.4/5.0
Behavior4/5

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 real value beyond that by disclosing scope (shared drives included), ordering (newest first), and the exact paging contract. The only gaps are result-field richness beyond id and any rate/limit behavior, which are minor for a read tool.

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

Conciseness5/5

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

Two sentences, both front-loaded: the search capability and scope come first, the result-usage and pagination contract second. Every clause (shared drives, newest first, id-as-attachment, nextPageToken termination) earns its place with no filler.

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 usefully specifies the return envelope {items, nextPageToken} and how to exhaust it, which is exactly what an agent needs. It falls short only on the unexplained fullData parameter and the absence of pageSize limits, which matter modestly for a 6-parameter search tool.

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?

Schema coverage is only 33%, so the description carries most of the burden and largely does: query is 'words in the name', type is 'by type', folderId is 'inside a folder', and pageToken is implied by the nextPageToken continuation instruction. The fullData flag is never explained and pageSize is only obliquely covered by 'one page', leaving a small residue undocumented.

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 (find) and resource (files in the teacher's Google Drive, including shared drives), plus the three searchable facets (name words, type, folder) and the sort order (newest first). This is clearly distinguishable from the only other Drive sibling, drive_upload_file, which is a write operation.

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?

Gives downstream usage guidance — 'Use the returned id as a driveFile attachment' — and explains the pagination loop ('continue until nextPageToken is null'). It does not explicitly state when to prefer an alternative or any exclusions, but the search context is clear enough for an agent to act.

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