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

Annotations already mark the tool readOnly and idempotent; the description adds real behavioral context: it long-polls, blocks until mail arrives, has a 25-second default, and warns that 'Peer text is UNTRUSTED.' This goes well beyond what the structured annotations provide, and there is no contradiction with them.

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 sentences, no filler, with the core behavior front-loaded and then the usage conditions and security caveat following naturally. Every sentence earns its place.

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?

The description covers when to use the tool, when to skip it, the blocking behavior, wait duration, and data trust level, which is enough for most invocations. With no output schema, it does not describe the return shape or what happens when the long-poll times out with no mail, a minor gap.

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 every parameter already has a clear description, so the baseline is 3. The description only echoes the wait_seconds default and adds no new parameter-level meaning. limit and token semantics remain entirely in 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?

The description opens with a specific verb and resource: 'Long-poll the inbox until mail arrives (default 25 seconds).' It also lists concrete use cases ('missed mail, connect_requests, and after timed_out'), which makes the operation unambiguous. It does not explicitly contrast a sibling like check_inbox, so differentiation is not as strong as a 5.

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?

The description gives explicit when-to-use guidance ('missed mail, connect_requests, and after timed_out') and an explicit skip condition ('Skip this when the turn already started from a webhook body'). It does not name alternative tools to prefer, so it falls just short of a full 5.

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