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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely useful behavior beyond that — matching is passage-level, results come with page URLs intended for quoting, and the query language must match the lang parameter. It doesn't discuss result-count behavior or matching confidence, which keeps it from 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 short sentences, front-loaded with purpose, then output form (quotable passages plus URLs), then the language rule. No filler or restatement of the title.

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-value shape needn't be explained; between the annotations and the description, an agent knows the corpus, the read-only closed-world nature, and the language constraint. The only gap — the meaning of limit — is minor for a 3-parameter search 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?

At 67% schema coverage, the schema documents query and lang but says nothing about limit (default 5, max 10). The description adds a non-obvious constraint on lang — the question must be phrased in that language — which the schema's "Language of titles, texts and stop names" does not convey. The limit parameter remains unexplained in either place.

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?

Uses a specific verb ("searches") on a clearly bounded resource: the site's own answer corpus, itemized as FAQ topics, destination/season guides, and sailing routes. This distinguishes it from lookup siblings like get_destination, get_route, or get_boat, which return structured records rather than best-matching passages.

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?

Clear context is implied by the enumerated content scope (licences, skipper, payment/deposit, cancellation, alerts, destinations, routes), telling the agent this is the tool for prose/semantic questions. It does not explicitly say when to prefer it over get_destination or get_route, leaving that inference to the agent.

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