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

Annotations already flag destructiveHint and idempotentHint, yet the description adds substantial non-obvious behavior: the preview page is removed, the share link and already-sent mail survive, and a confirmation prompt shows recipient/subject/sent status. It also discloses error semantics (not_found for expired/foreign renders, forbidden with details.code needs_person and a resolveUrl for locked emails), which no annotation conveys.

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?

Front-loads the destructive effect in the first sentence, then layers side effects, confirmation, and error codes in descending priority. The parenthetical explanation of a locked email is slightly convoluted but earns its place by making an otherwise cryptic error actionable.

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 destructive tool with no output schema, it covers side effects, the confirmation flow, and failure modes well. It does not describe the shape of a successful response beyond the act of deletion, leaving that inferred.

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 baseline is 3; the description still adds meaning by explaining the confirmation preview that the confirm and confirmationToken parameters correspond to. It does not restate constraints on alwaysAllow or renderId format (left to the schema), which is appropriate.

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 ("Deletes one rendered email permanently, with its preview page") and immediately disambiguates scope by saying the recipient's share link is untouched, which separates it from the delete_share_link sibling. An agent can tell exactly what is being removed versus preserved.

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?

Clearly frames the deletion context and the confirmation precondition ("LinkDrop asks the person to confirm before it acts"). It does not name sibling alternatives such as delete_email_asset or delete_email_template and when to prefer them, so it stops short of full when/when-not guidance.

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