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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial behavioral context they cannot: the exact tri-state semantics of verified filters (true = official site says yes, false = explicitly no, unknown excluded), the provenance rule that the 'verified' object only contains facts read on the official website, and that booking_link redirects to the official site with src=entityindex.

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 dense paragraph, front-loaded with purpose before filters and return behavior, with no filler sentences. The filter enumeration is long but each clause adds a distinct semantic that the schema lacks.

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 an 11-parameter search with no output schema, the description covers filter meaning, verification provenance, and the shape of returned booking links. The only gap is pagination/result-count behavior (the 'limit' parameter) and no explicit sibling routing.

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 only 36%, so the description carries real weight, and it does: it defines the verified-boolean contract for spa/pool/parking/pets/ski_in_out/family, explains area as parish or locality with concrete examples, and clarifies min_stars as the category stated on the official site. Only 'limit' is left entirely to 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 a specific verb and resource ('Search accommodation in Andorra') plus the indexing source (entityindex.ai), so the domain is unambiguous. It never names its siblings get_hotel or list_areas, so the agent gets no explicit routing signal beyond the verb 'search' versus 'get'/'list'.

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 details which filters exist and how they behave, which implies when the tool is useful, but never says when to prefer get_hotel or list_areas, nor states prerequisites or exclusions. Usage must be inferred from the filter list.

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