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

Annotations already declare destructiveHint=true and idempotentHint=true, but on their own they would make the action look irreversible. The description adds the crucial nuance that Trash is recoverable and mail is never permanently deleted, plus the policy-forbidding constraint — three behavioral facts not present in any structured field. Return shape is covered by the output schema, so no gap remains.

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-loaded with the core action and recoverability, then the usage rule and the alternative. The trailing example payload largely duplicates what the fully documented schema already shows, so it does not fully earn its place, but the rest is dense and waste-free.

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?

A single-parameter mutation tool with rich annotations and an output schema needs exactly this: recoverability, an alternative for the adjacent intent, and a stated permission constraint. Nothing an agent needs in order to choose and call it correctly 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% and the message_id parameter is already documented as a `msg_…` id from a list or search. The description's inline example restates the same key and format rather than adding syntax, constraints, or edge cases beyond the schema. Baseline 3 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 ("Moves a message to Trash") plus the scope constraint that the message remains recoverable. It also names the sibling it is not (mail_archive) and the related mail_move domain, so an agent can distinguish it without opening any schema.

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 an explicit when ("only when the user wants mail deleted") and an explicit alternative ("to tidy the Inbox use mail_archive"). It also flags a precondition — the account policy can forbid the operation — so the agent knows a failure mode up front.

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