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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description earns credit by adding the irreversibility framing ('Permanently', 'no undo') and a required human-confirmation step, which annotations alone do not convey.

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 short sentences, front-loaded with the action and its consequence, then the safeguard. Nothing redundant and nothing padded.

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 delete with an output schema present and annotations covering safety, the description covers what an agent needs: permanence, no undo, and the human-confirmation requirement. Return values are handled by the output schema.

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 required parameter with 0% schema description coverage, so the description must carry the load. 'Confirm the exact message' implies the parameter identifies a specific message, but it adds no format or disambiguation guidance beyond the self-explanatory name message_id.

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?

Specific verb and resource ('permanently delete a saved outgoing copy') that an agent can distinguish from the many sibling delete tools (delete_message, delete_draft, delete_thread) by the 'outgoing/sent' qualifier. No schema opening needed to know what it targets.

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 instructs the agent to confirm the exact message with the human before acting, which is a real usage precondition. It does not, however, name the alternative tools (e.g. delete_message vs delete_sent_message) or state when this should be preferred.

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