Empty trash

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

Annotations only flag destructiveHint=true; the description goes further by naming the irreversibility, the mandatory confirmed=true gate, and the review-before-confirm protocol. This is real behavioral context an agent needs before firing a bulk-destructive call.

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?

Three short sentences, front-loaded with the destructive scope, then the precondition, then the sibling routing. No filler, every clause 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 one-parameter, no-output-schema bulk-destructive tool, the description supplies scope, irreversibility, the confirmation requirement, and the safe operating procedure. Nothing an agent needs to invoke it correctly is missing.

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% and the single parameter already carries a description ('Must be true; the user has reviewed the trash...'), so the description's restatement of 'Requires confirmed=true' adds nothing new. Baseline 3 is correct when the schema does the work.

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?

States a specific verb ('Permanently delete') plus resource and scope ('ALL items in the Proton Drive trash'), and immediately marks the operation as irreversible. It also distinguishes itself from the two nearest siblings, drive_delete (individual items) and drive_list_trash (review step).

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?

Gives an explicit pre-call workflow ('Call drive_list_trash first, show the user exactly what will go, and get explicit confirmation') and names the alternative for the other case ('For individual items use drive_delete'). Both when-to-use and when-not-to-use are covered.

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