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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real behavioral detail beyond them: the result is capped at 10, ranked by Hotel Please medals, and each entry carries standout reason, medals, Michelin Keys, typical price, and booking links. No auth or rate-limit notes, but nothing is contradicted.

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?

Front-loads the core purpose in the first clause, then narrows to filters and examples in a logical order. The result-fields sentence is a long run-on list, which slightly hurts scanability but every element is informative.

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?

There is no output schema, so the description must describe returns and it does so thoroughly (ranked list with medals, Keys, price, profile and booking links). Combined with the 100% schema coverage, an agent has enough to call this correctly; only the search-vs-detail boundary with get_hotel is left implicit.

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 100% and every parameter (vibe, limit, place, facilities, price_tier, michelin_keys) is already documented in the schema, including the vibe enum meanings. The description largely restates those options, so the baseline 3 is right; it adds only the emphasis that limit tops out at 10.

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 concrete verb and resource ('Where to stay in a city, country or neighborhood') plus the exact shape of the result set: up to 10 profiled hotels ranked by medals. This is specific enough to separate it from the sibling get_hotel, which the phrase 'a link to its full profile' implicitly routes to.

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?

Gives four worked query examples ('where should I stay in Kyoto', 'design hotel with a pool in Bangkok') and enumerates the narrowing dimensions (vibe, facility, Michelin Keys, price tier), which effectively tells the agent when this tool applies. It stops short of naming when to prefer the sibling get_hotel over this search.

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