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

Annotations only declare destructiveHint/idempotentHint; the description goes further by disclosing that the delete is a soft delete (moves to Trash), that it is reversible via restore_sent_message, and that the retention window is seven days before permanent deletion. That recovery model is exactly the context an agent cannot get from the annotations.

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 tight sentences, front-loaded with the action and the human-confirmation gate, then the reversibility consequence. No filler.

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 single-parameter destructive tool with an output schema already covering returns, the description supplies the missing lifecycle and recovery context. Nothing an agent needs to call it correctly is absent.

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?

One parameter at 0% schema description coverage, so the description carries some burden. 'Confirming the exact message' implies message_id identifies the target, but it adds no format, UUID, or lookup guidance beyond what the schema's type/pattern already encode.

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 (Delete) and a precisely scoped resource (a sent email's saved copy), which cleanly separates it from the sibling delete_message and delete_draft. The scope word 'sent' plus the Trash semantic makes the target unambiguous.

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 a clear precondition ('after confirming the exact message with the human') and names the recovery alternative restore_sent_message with its seven-day window. It does not explicitly say when to reach for delete_message vs this tool, so it stops short of full alternative routing.

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