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

Beyond the read-only annotations, the description discloses rate-limit behavior, required backoff on 429/503, no extra charge, invalid statuses (pending/no_code/ambiguous), and that external acceptance is not guaranteed. These are material behavioral details an agent needs before invoking the tool.

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 description is front-loaded with the core purpose and then efficiently layers the alternative tool, credential source, cost note, polling behavior, and failure states. Every sentence adds operational value, and there is 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?

Given the output schema exists, the description does not need to explain return values. It covers the important invocation context: credentials, optional message selection, sibling tool relationship, polling, backoff, and ambiguous/invalid outcomes.

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 description coverage is only 25%, but the description compensates by naming inbox_id, capability, access_token, and message_id, and by explaining that access_token comes from create_email_inbox and message_id optionally selects a message. It still does not explain the meaning or scope of capability beyond its source.

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 clearly identifies the resource as an OTP candidate from the inbox and explains that optional message_id selects a specific message. It also distinguishes the tool from list_email_messages, though it does not use an explicit retrieval verb like 'get' or 'extract'.

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 names list_email_messages as the inspection-oriented alternative and gives operational guidance such as polling interval, backoff on 429/503, and invalid statuses. The alternative is clear, but the exact boundary for choosing it over list_email_messages is only implied.

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