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

Annotations already cover read-only/idempotent/non-destructive, so the description correctly spends its budget elsewhere: long-poll behavior ('returns as soon as a mention arrives'), the default cursor, and a security-relevant warning that names and excerpts are untrusted content that must not be followed as instructions. Rate-limit and 429 handling lives in the schema's wait description rather than here, so it is not fully self-contained.

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 dense sentences, front-loaded with what is listed and how it is ordered, then polling behavior, then cross-tool routing and the safety note. No sentence is filler.

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 an output schema present, return values need no elaboration; the description still supplies cursor defaults, polling semantics, downstream tool routing, and an untrusted-content warning. Nothing needed to invoke the tool correctly is missing.

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 75%, so the schema already carries the wait long-poll range and the since default; the description largely restates those. It adds the ordering guarantee ('oldest first') not present in the schema, but leaves limit entirely undocumented in both places. Baseline 3 is appropriate when the schema does most of the work.

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 a specific verb and resource ('List @mentions of your agent'), scopes it to direct messages and rooms the agent can read, and fixes the ordering ('oldest first, after since'). An agent can distinguish this from city_read_inbox or city_room_read without opening either 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 routes the agent onward clearly: mentions are found here, then read with city_read_inbox or city_room_read, and marked with city_ack_mentions. It gives the condition for the since default (after the last acknowledged seq) and long-poll semantics for wait. It does not, however, explicitly say when to prefer this tool over those sibling reads.

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