Skip to main content
Glama

Drive checkup

drive_checkup
Read-onlyIdempotent

Generate folder health report with 0-100 score and findings for duplicates, empty folders, large old files, public links, outside access, exposed sensitive names, and trash, without changing files.

Instructions

Health report for a folder in one call: exact-duplicate candidates, empty folders, large old files, public links, outside access, sensitive-looking names in shared items, trash. Score 0-100 (scoreParts), counts and at most 3 example paths per finding (namesInResult counts them); names, sizes, dates, sharing only, no content. finding= returns one page. Cached walk (5 min); partial:true means call again. Changes nothing.

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_checkup"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoFolder under /my-files (default /my-files).
limitNoPage size (default 50).
offsetNoItems to skip.
findingNoOne page of this finding instead of the summary.
refreshNoIgnore the cached walk.
sharingNofalse skips the sharing calls (link expiry unknown).
minSizeMBNolarge-old size (default 50).
olderThanDaysNolarge-old age (default 365).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description usefully reinforces this with 'Changes nothing', plus discloses caching ('Cached walk (5 min)'), a partial-result retry contract ('partial:true means call again'), and a data-scope limit ('names, sizes, dates, sharing only, no content'). However, those are the only behaviors covered – nothing about rate limits, cost of the sharing calls when enabled, or failure modes – so against the lower annotation-adjusted bar it is solid but not rich.

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 outcome, then return shape, then drill-down, then caching caveats – dense and mostly waste-free. It leans on telegraphic jargon (scoreParts, namesInResult) that assumes the caller will infer meaning from field names.

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?

Despite having no output schema and eight parameters, the description enumerates the return fields (0-100 score, scoreParts, counts, at most 3 example paths per finding, namesInResult, partial), the caching behavior, and the read-only guarantee. An agent has enough to call it correctly and interpret the response.

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 every parameter including the finding enum, limit/offset, refresh, sharing, minSizeMB and olderThanDays is already documented. The description restates a few of these defaults and the meaning of 'finding' rather than adding syntax, interaction rules (e.g. whether limit/offset apply to the summary), or constraints beyond the schema.

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 ('Health report for a folder') and enumerates exactly the seven finding categories it produces, so an agent can tell this aggregate report apart from siblings like drive_find_duplicates or drive_cleanup without opening a schema.

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?

Implies clear context ('health report in one call') and explains the drill-down path: summary first, then 'finding=<id> returns one page'. It does not name alternative sibling tools or state when a narrower tool would be better, so it stops short of full when/when-not guidance.

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