Trash many items

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

Discloses behavior well beyond annotations: the 200-item cap, the dry-run/plan semantics, the gating on problem detection, and the explicit user-approval prerequisite for the write path. The reversibility framing (drive_restore recovers) is also stated, consistent with destructiveHint=false.

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?

Four short, front-loaded sentences that each carry distinct information (scope, recovery path, dry-run behavior, execution gate). No filler or repetition.

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 two-parameter mutation tool with no output schema, the description covers purpose, prerequisites, and both execution modes adequately. It could say more about the shape of the returned plan/problems, but nothing essential for correct invocation 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%, so the schema already documents both parameters (baseline 3). The description adds real meaning beyond it by explaining that confirmed=true asserts execution only after problem-free validation and explicit approval, not merely a boolean flag.

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 and resource ('Trash up to 200 items') with an explicit scope limit, and immediately names the recovery sibling (drive_restore). This distinguishes it from single-item drive_trash and from drive_empty_trash.

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?

Explicitly spells out both modes: without confirmed it only produces a plan and problems, with confirmed=true it executes only when no problems exist, and it requires confirmed=true after explicit user approval. The when-to-use and when-not-to-act conditions are fully covered.

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