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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds real behavior beyond them: results are capped at 8 pages and include title, kind, URL and a short snippet, and it tells the agent what to do next (fetch details or hand the guest the URL). Minor gap: nothing about ranking or what to do when nothing matches.

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 sentences, front-loaded with what the tool searches, then when to reach for it, then what comes back. Every clause carries information; the example query terms and the result shape are the only elaboration and both earn their 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?

With an output schema, rich annotations and fully described parameters, the description needs only to cover selection guidance and result behavior, which it does. The one soft spot is the unexplained "kind" field and no note on empty-result behavior, but neither is required for correct invocation.

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 description coverage is 100% and both parameters (query with min/max length, language enum with default) are documented in the schema. The description only adds a light gloss — that the search runs in a single language and that short single-word queries like "dogs" or "sauna" are the intended input — which is a marginal supplement to the schema, so the baseline 3 applies.

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 gives a specific verb and resource ("Full-text search over the pages of mondschein.com") plus the scope constraint ("in one language") and enumerates the content types covered (houses, rooms, dining, wellness, blog articles). An agent can immediately tell this apart from structured siblings like list_rooms or get_weather.

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 states a clear routing rule: use it "when no other tool fits or to find the right page for a question," with concrete example queries ("dogs", "sauna", "Lech", "parking"), and points onward to the matching detail tool. The when-not side is expressed only as the generic "no other tool fits" rather than naming which sibling covers which content domain, so it stops just short of fully explicit alternatives.

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