drive_trash_file

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

The description adds genuine value beyond the annotations by disclosing that trashing is recoverable rather than permanent, which matters for an agent deciding whether to warn a user or offer an undo path. destructiveHint=true and readOnlyHint=false are consistent with the stated behavior, so there is no contradiction. It also names the return payload, though that partly duplicates the output schema.

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 two short sentences with the core action front-loaded and the key nuance (recoverable) in a parenthetical in the same breath. The 'Returns' block is slightly redundant with the existing output schema but is brief and usefully names the confirmed fields. No filler, repetition of annotation flags, or wasted words.

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 one-parameter mutation tool with annotations covering destructiveness and idempotency, and an output schema covering the return value, the description covers the essentials: what it does, that it is recoverable, and what it returns. It omits minor context such as required scopes/permissions, behavior for missing files, and whether folders are supported, but these are low-stakes at this complexity level.

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?

The tool description adds no parameter semantics beyond the schema, and the context signal reports 0% schema description coverage for the top-level input object, so the description carried the burden to compensate and did not. Practical harm is limited because the single parameter's meaning is evident from the file_id name and the schema's own property description. The description does not document formats, required scopes, or invalid-ID behavior.

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 uses a specific verb-resource pair ('Move a Drive file to the trash') and immediately clarifies scope with 'recoverable, not permanent deletion,' preempting the most common confusion about this operation. The sibling set contains no other trash/delete tool, so there is no ambiguity about which tool this is. The annotation title reinforces the same purpose.

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?

No explicit guidance on when to use this tool versus alternatives; usage must be inferred from the stated action. The sibling set has no permanent-delete tool, and the description never discusses that alternative, though the 'recoverable' parenthetical implicitly contrasts with permanent deletion. This is adequate but leaves context to inference.

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