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

Annotations only give readOnlyHint=true; the description carries the real behavioral load: the 60s ceiling is per-call not the inbox lifetime, the inbox does not self-delete or become unusable after a match, it stays valid ~2 weeks, and 'expired' is not final until retried. That is exactly the context an agent cannot 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?

Front-loads the core action and the required parameter before the edge-case guidance, and every sentence carries non-redundant operational detail; it is long and parenthetical-heavy, but nothing is 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?

With no output schema, the description still explains the meaningful return condition (expired) and how to interpret it, plus retry cadence and inbox lifetime — an agent has everything needed to call and interpret this correctly.

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 goes beyond the schema by insisting on the exact address returned by create_trial_inbox and by clarifying that ttl_seconds caps a single blocking call rather than the inbox's total validity — a distinction the schema's 'max 60' alone does not convey.

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 ('Block ... for the one confirmation email on a trial inbox') and names the creating sibling (create_trial_inbox) whose output feeds it, so it is unmistakable against await_trial_inbox_claim, claim_trial_inbox, and create_trial_inbox.

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?

Explicit when-to-call ('AFTER you have actually used the address somewhere') plus when-not ('calling it before that will just expire'), the retry rule for >60s senders, and the alternative claim_trial_inbox path if the human wants to keep the address.

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