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

No annotations exist, so the description carries the full burden. It discloses one useful behavioral fact (results are capped at the 50 most recent, so older bulletins are unreachable), but says nothing about auth requirements, result ordering, or whether keyword matching is case-sensitive/partial, and never confirms the operation is read-only beyond the word 'search'.

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?

A single compact sentence with the useful constraint (50 recent) front-loaded. The leading 'PRO.' is unexplained noise that costs clarity without earning its place.

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 two-parameter read tool with no output schema and no annotations, the description covers the essentials of what it returns (a capped list of bulletins) but omits return shape, ordering, and whether an empty keyword means 'all recent'. Adequate, not complete.

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 50%: access_token is documented in the schema, while keyword is only typed as a bare string. The description compensates by explaining that keyword filters on title/office, which tells the agent what the match targets — meaningful value beyond the schema.

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 the resource (tsunami bulletins), the recency/scope limit (up to 50 recent) and the keyword filter, which is enough to distinguish it loosely from latest_tsunami and active_only. It stops short of explicitly naming how it differs from those siblings, leaving the agent to infer the contrast.

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?

Usage is only implied: 'recent' and the optional keyword filter suggest a browsing/search tool, but there is no statement of when to choose it over latest_tsunami or active_only, and no prerequisites are mentioned. The leading 'PRO.' token gives no actionable guidance.

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