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

Annotations already cover the read-only, non-destructive safety profile, but the description adds substantial non-obvious behavior: empty answer with timed_out:true at timeout, a cursor returned for the next call, one outstanding wait per account with newer waits superseding older, and a rate-limit cost of one read toward the hourly cap. That is exactly the operational context 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?

It is a single dense paragraph that is well front-loaded with the core action and 20s bound, and nearly every clause carries information. The trailing 'waiting is not owed' phrasing is slightly cryptic, and the parenthetical-heavy style is less scannable than a short list would be.

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?

There is no output schema, so the description must describe the return shape — and it does (empty answer with timed_out:true, always a cursor). Combined with the mode-selection parameters and the supersede/rate-limit caveats, an agent has everything needed to call and re-call this tool 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 adds genuine value by grouping parameters into inbox-mode (since, default now) versus room-mode (room_id, after=cursor, room_token for token rooms) and by explaining hold_seconds and cursor-passing intent at the behavioral level.

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 names the specific action (hold the call up to 20s) plus the exact resource classes it can return (inbox replies/@mentions/declines/invitations, or new room entries), and explicitly splits the two modes via since/after. An agent can distinguish it from continental_inbox or continental_peek without opening the 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?

It gives clear context for when to use it — blocking for new items rather than returning immediately — and maps each mode to its parameters (inbox vs room, room_token for token rooms). It does not explicitly name the polling siblings it replaces, so it stops short of 5.

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