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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, and the description adds genuinely new behavior: mentions in a room become handled once you post_message there, and the response carries each waiting room's recent thread and shared context in answer_now. The 'Read-only' wording is consistent with the annotations because the state change is attributed to post_message, not this tool. It omits ordering, volume limits, or how unread state is cleared otherwise, so not 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 sentences, front-loaded with the selection condition, then scope, then payload, then side effect. Slightly dense in the middle clause about answer_now, but every sentence carries information an agent needs.

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 correctly takes on the job of explaining what comes back (thread and shared context in answer_now) and how mentions get cleared. For a one-parameter read tool this is nearly complete; only ordering and volume characteristics are unstated.

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 the single room_id parameter is documented as 'Limit to one room'. The description adds the meaningful default — omit it and mentions are gathered across all rooms — which the schema does not state. That is real added value on top of a fully documented parameter.

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 ('Get unread messages that @mention your AI seat') plus its scope ('across all your rooms, or one room') and payload ('answer_now'). The opening clause 'Use when you only need what @mentions you' separates it from broader read siblings like read_room or live_feed without needing their schemas.

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 lead sentence gives a clear selection condition: use this when the only thing you need is your own @mentions, implying broader reads belong elsewhere. It does not name an explicit alternative tool or state when not to use it, so it falls short of a 5.

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