Upload a local file to Google Drive

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds valuable behavioral context: conversion rules for various file types, default destination, and error behavior with next_steps. It does not contradict the annotations and provides meaningful detail beyond them, though it could mention potential side effects like overwriting existing files (though it doesn't, which is fine as it's not destructive).

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

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

The description is concise yet comprehensive, with each sentence adding distinct value. It is front-loaded with the core action and return value, then logically progresses to conversion behavior, destination, and error handling. No wasted words; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters, all documented, and no output schema, the description is complete. It explains return value (URL), conversion behavior, folder handling, and error handling. The complexity is moderate, but the description covers all necessary aspects for an agent to invoke it correctly, including edge cases like folder_id visibility.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters have descriptions. The description significantly enhances this by explaining the convert enum in detail (what happens with auto, which file types map to which Google format), cautioning about folder_id with drive.file scope (404 risk), and clarifying the name default (extension dropped when converting). This goes well beyond the schema's terse descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (upload a local file), the target (Google Drive), and the outcome (return its URL). It also details conversion behavior for different file types, which distinguishes it from any potential sibling upload tools. The verb 'upload' is specific and the resource is unambiguous.

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

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

The description provides clear context on default behavior (My Drive root) and when to use folder_id, and it explains error handling when drivelift is not set up. While it doesn't explicitly state when not to use this tool or name alternatives, the sibling tools are all auth/setup related, so the usage context is clear. It could be more explicit about prerequisites (e.g., auth required), but the mention of drivelift setup covers that.

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