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

Annotations already provide readOnlyHint and openWorldHint. The description adds meaningful behavior: long-polling semantics, immediate return on a new message, empty return after the timeout, and efficiency characteristics. No annotation contradiction is present.

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?

The description is two sentences, front-loaded with the core action and condition, and contains no redundant or filler wording. Every clause contributes to selecting or invoking the tool correctly.

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?

For a relatively simple tool with full schema parameter coverage and safety annotations, the description covers the trigger, timeout behavior, return condition, and when to prefer it. No output schema is present, but the return behavior is sufficiently described as a message or empty.

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 the baseline is 3. The description adds value by explaining `since` as a sequence threshold ('newer than `since`') and `seconds` as the time after which an empty result is returned, which goes beyond the schema's brief property texts.

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 'Long-poll a room,' a specific verb and resource, and explains the exact condition ('returns as soon as a message newer than `since` lands, or empty after `seconds`'). It clearly separates this from ordinary reads but does not explicitly name a sibling like read_room, so it stops short of a perfect 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 guidance is explicit: 'Cheaper and faster than repeated reads — prefer this over polling.' This tells the agent when this tool is the right choice, though it does not name a specific sibling alternative to use when polling is not desired.

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