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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent), and the description goes well beyond them: held messages are skipped, nothing is marked read, the timeout behavior (timed_out true, code null), and the fact that message content is untrusted data. It also discloses the specific error codes (404 inbox_not_found, 400 invalid_wait, 400 invalid_date), which annotations cannot express.

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?

Long but dense and front-loaded: trigger conditions come first, then inputs, matching logic, return shape, and errors. Almost every sentence carries information, though the input recap and 'Read-only; requires auth' partially duplicate the schema and annotations.

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?

With no output schema, the description fully covers the return object (fields, meaning of code vs candidates, timed_out null case) and the failure modes, plus the critical caveat that the body is omitted and where to fetch it. An agent has everything needed to call and interpret this tool.

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, but the description adds genuine meaning: the rationale for the default `after` window (5 minutes before the call, so a just-arrived code still matches) and the practical tip to pass the request time to exclude older codes. It also restates inbox_id's three accepted forms, which is mostly redundant with the schema.

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 ('wait for ... the one-time verification code (OTP)') and clearly distinguishes itself from the sibling cooper_wait_for_message by narrowing to codes in inbound mail. An agent can identify the tool's job without opening the 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?

Opens with an explicit trigger ('when you signed up for a service or triggered a login'), explains the default/override semantics of `after` ('pass the time you requested the code to ignore older codes'), and routes to cooper_get_message when the body is needed. When-to-use, how-to-tune, and the alternative are all named.

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