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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is low, yet the description adds real behavior: the blocking duration, the retry loop on timeout, and a full literal return shape including the timed_out discriminator. It omits error/failure conditions (bad address, expired secret), which keeps it short of a 5.

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?

Three tight sentences, each carrying distinct information: cap, return shape, retry rule, filtering parameter. No repetition of the title or annotations, and the return shape is front-loaded after the timeout constraint.

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 supplies the return contract itself (both the success message fields and the timeout case), plus the retry and filtering behavior. That is everything an agent needs to drive a polling loop 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 description coverage is 100%, so all four parameters are already documented and the baseline is 3. The description reinforces `since` semantics ('ignore mail you've already seen') and the 25s cap, but adds little beyond what the schema fields already say.

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 an email') plus the scope constraint ('up to 25 seconds') and ties itself to a sibling ('a mailbox made with create_mailbox'). An agent can distinguish this from list_messages without opening either 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?

Explicitly tells the agent to 'call again on timeout', which is the key usage pattern, and explains when to pass `since` ('to ignore mail you've already seen'). It never explicitly contrasts itself with list_messages, so the alternative-selection guidance is implied rather than stated.

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