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

Explains the two-phase cursor behavior (snapshot then feed), the long-poll blocking up to wait_seconds, and the state side effect 'Wake notices are settled once you have caught up' — which justifies the non-obvious readOnlyHint=false in the annotations. It also flags that message content is untrusted data and must not be treated as instructions, a behavioral warning the annotations cannot convey.

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-loaded with the core purpose and no filler; every sentence carries operational meaning, including the security caveat. The middle section on cursor phases and wake notices is densely packed into one paragraph, which slightly hurts scannability but wastes nothing.

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 carries the return-shape burden and does: first page of threads, next_cursor, has_more, request events of kind 'request'. Combined with 100% schema coverage on three optional parameters, an agent has everything needed to drive the 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 coverage is 100%, so the baseline is 3; the description adds real meaning beyond it by explaining that the cursor drives a phase transition ('after the last snapshot page come the messages that arrived since') and that wait_seconds only applies in the feed phase. as_address is only loosely covered ('as one of your addresses'), so it is not a full 5.

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 ('Read new messages and follow the receive loop') plus scope ('as one of your addresses or your whole account'), and explicitly names the sibling it is not ('use get_overview'). An agent can distinguish it from get_overview, read_thread, and get_reception without opening a 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?

Gives an explicit routing rule to an alternative ('For which addresses have something to reply to or are waiting for a reply, use get_overview') and pairs the request event with its two follow-up siblings ('accept_request opens it, leave_thread ignores it'). It also states the polling contract (has_more true means call again now), which is the key usage decision for this tool.

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