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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description nonetheless adds real value with the 20-item cap, newest-first ordering, user-level (not company-level) ownership, and the returned fields including body formatting and optional link. The only shortfall is that it does not say what happens when more than 20 alerts exist (truncation vs. pagination), which an agent calling with a hard cap needs to know to report accurately.

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-loads what the resource is and its bounds before the trigger condition and the dismissal caveat, which is the right order for an agent skimming. It is denser than strictly necessary — the three illustrative alert types and the detailed body-format aside could be trimmed — but every sentence carries information rather than restating the name.

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 return-shape burden by describing heading, body, link and kind, which is enough for an agent to present alerts sensibly. The unresolved gaps are what the 'kind' values can be and why a required company_id exists for user-scoped data — minor but not trivial for a single-parameter tool.

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 schema already explains company_id by reference to list_my_companies, so the baseline is 3. The description adds no syntax or format detail for the parameter, and its claim that alerts 'belong to the USER, not to one company' sits in mild tension with the required company_id, leaving the agent to infer why a company scope is needed for user-level data.

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?

Names a specific resource (the user's unread/unaddressed YESbusiness announcements) and immediately bounds it with ordering and volume (newest first, 20 at most), plus concrete examples of what an alert is (congratulation on accounting creation, team notice, outstanding step). No sibling tool covers alerts, so ambiguity with export_report or list_bookings is nil.

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?

Gives an explicit trigger ('when the user asks whether anything needs their attention or what YESbusiness told them') and an explicit capability boundary ('you cannot dismiss one — the user does, on the dashboard'), which prevents an agent from promising or attempting a write. That negative guidance is exactly what distinguishes a usable listing tool from a frustrating one.

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