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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower, but the description adds real behavioral facts they don't carry: the 30-day window, user scoping via ctx.userId, and a hard 200-notification scan that can silently omit older mentions. That cap is genuinely useful for interpreting completeness of results.

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 verb, audience, and time window in the first sentence. The final sentence mostly restates cheaply useful content (the 200 cap) but wraps it in internal implementation language ('Implementation matches the route') that is not relevant to a caller.

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 zero-parameter, read-only list tool, the description covers source, scope, window, and the truncation limit. With no output schema it could go further and hint at the shape of a mention (id, task, comment, timestamp), but nothing critical to correct invocation 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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter semantics to get wrong. The description correctly implies there is no filtering or pagination input to supply.

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 ('List @-mentions') with clear scope: the calling user, last 30 days, scoped to ctx.userId. It is distinguishable from generic notification tools in intent, but it never explicitly names or contrasts the closest sibling (list_notifications), which also returns mentions among other types.

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?

There is no when-to-use / when-not-to-use guidance and no mention of alternatives. Given the crowded notification family (list_notifications, mark_notification_read, list_recent_activity), an agent gets no help choosing this tool over list_notifications, which likely covers the same data plus more.

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