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

Annotations already declare destructiveHint=true and idempotentHint=false, so the bar is lowered. The description still adds value by emphasizing irreversibility, storage reclamation, and the explicit-confirmation step, but says nothing about batch limits, partial failures, or auth requirements.

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?

Two sentences, zero padding, with the destructive outcome and the confirmation gate front-loaded in that order.

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 an irreversible destructive tool with no output schema, the definition covers the essentials but leaves gaps: behavior when an ID is not in Trash, the batch-size ceiling, and failure semantics are unstated. Adequate but not complete.

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 0%, so the description must compensate. It clarifies that confirmPermanent must be true and that mediaIds should reference trashed items, but omits the 200-item cap and the UUID format enforced by the schema.

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 ('irreversibly deletes selected items') and narrows scope with 'already in Trash', which implicitly separates it from trash_media and restore_media. It does not name those siblings explicitly, so an agent must infer the routing.

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 phrase 'already in Trash' carries a real precondition, and the confirmation requirement is stated. However, it never says what to do instead when items are not yet trashed (trash_media) nor what happens if confirmation is skipped, leaving usage conditions implied rather than explicit.

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