Skip to main content
Glama
Google Workspace (GWS) MCP Server

Google Workspace (GWS) MCP Server

drive_files_update

DestructiveIdempotent

Update a Drive file's name, MIME type, or content. Provide an uploadPath to replace the file's content, noting the previous content is not kept.

Instructions

Update a file's metadata or content. An uploadPath replaces the file's content and no copy of the old content is kept. Because it can do that, the whole tool is marked destructive, including calls without uploadPath.

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": {
      "fileId": "<fileId>"
    },
    "name": "drive_files_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNew file name
fieldsNoFields to return
fileIdYesThe file ID to update
mimeTypeNoNew MIME type
uploadPathNoLocal file path to upload

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description had a lower bar, yet it still adds real value: it discloses that uploadPath permanently replaces content with no copy retained. The final sentence explains why the whole tool carries the destructive flag, preventing a misread that only uploadPath calls are destructive. It stops short of covering who may call it or what a no-op update returns.

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?

Three short sentences, action first, destructive consequence second, annotation rationale third; nothing is repeated verbatim from the schema and every sentence carries load-bearing information.

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?

For a 5-parameter tool with full schema coverage, no output schema, and rich annotations, the description covers the one behavior an agent could get wrong (irreversible content replacement). It is slightly light on permission requirements and on what a metadata-only update returns, but nothing essential to correct invocation is missing.

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 100%, so the baseline is 3, and the description earns above that by adding semantics the schema's "Local file path to upload" does not convey: that this parameter overwrites the file's current content irreversibly. The other four parameters (fileId, name, mimeType, fields) are left entirely to the schema.

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?

States a specific verb and resource ("Update a file's metadata or content") and immediately narrows the scope by naming the content-replacement path. An agent can distinguish it from drive_files_create/copy/delete by the update semantics, though the description never names a sibling 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?

It implicitly tells the agent that uploadPath is the way to replace content versus plain metadata edits, which is useful mode selection. However, there is no when-to-use/when-not guidance against siblings (create, copy, delete) and no statement of prerequisites such as write permissions or ownership.

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