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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds useful behavior beyond that: results are live-priced, the response is a paginated list with prices/ratings/amenities, and per-room entries change what the returned prices cover.

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 purpose and scoping, then filters, then the multi-room special case, then the return shape. The amenities parenthetical is long but each item is a real accepted value, so little waste.

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 33-parameter search with no output schema and zero schema descriptions, the description covers the headline filters and return shape, but leaves a large set of filters and all pagination/sort/currency semantics unexplained. Adequate, but an agent will guess on many parameters.

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 0% across 33 parameters, so the description must carry the load. It helps with the highest-value ones (price range, stars, property type, free cancellation, breakfast, a long but partial amenity list) and explains the non-obvious `rooms` semantics, but many parameters (sort, page_size, currency, residency, min_bedrooms, room_capacity, club_room, taxes_included, pay_at_hotel, no_card_needed, bed_type, room_view, region_id) remain undefined in both schema and prose.

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 hotels in a city or region') plus the distinguishing capability of live prices and availability. It does not name or distinguish itself from siblings like search_hotels_by_geo or get_hotel_details, which matters given the crowded hotel tool family.

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 implied by 'in a city or region' and by the multi-room pricing note, but the description never says when to pick this over search_hotels_by_geo, get_nearby_hotels, or get_hotel_details. No exclusions or prerequisites are stated.

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