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

Annotations only flag destructiveHint and idempotentHint; the description goes well beyond them by disclosing the concrete consequences — all mail is destroyed, and the hosted address is never reissued, so third-party sign-ups tied to it are unrecoverable. It also carries a security note about untrusted message content and a required user confirmation, which is behaviorally meaningful context an agent would not get from the structured fields.

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?

The irreversible consequence and the confirmation requirement are front-loaded in the first two sentences, which is exactly where they belong. The final sentence about untrusted message content is a general safety policy only loosely tied to a delete operation, so it adds length without much tool-specific value.

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 and full annotation coverage, the description supplies the two things an agent most needs: permanence of the deletion and the address never being reusable. Combined with the confirmation instruction, nothing essential to calling this safely 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 single parameter already documents its three accepted forms (mbx_ id, address, external id). The description adds no further meaning about the identifier or how it is resolved, so the baseline of 3 applies — the schema does all the work here.

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?

The description states a specific verb and resource — 'Delete a mailbox and all its mail' — and adds scope that the name alone doesn't convey: the deletion is permanent and includes every message in it. It does not, however, differentiate this from related siblings such as forward_mailbox or delete_webhook, so an agent still has to infer that this is the only true destructive mailbox operation.

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?

It provides a procedural precondition ('confirm with the user first'), which is real guidance on how to call it. But it offers no selection guidance — no mention of when to delete versus forwarding, archiving, or simply listing mailboxes, and no statement of the conditions under which deletion is appropriate beyond the bare confirmation step.

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