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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: 10 results per page, ranking order with tie-breaking on review count, a caveat that thin-review hotels are pulled toward the destination average, and the important rule that hotel_name causes other filters to be ignored. 'Read-only, no sign-in' merely restates the annotations, and pagination cap of 5 pages is only in the schema.

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?

The trigger is correctly front-loaded, but the second sentence is a single sprawling construction with nested parentheticals containing Comfort Score weighting percentages (60/30/15/15/10) that are expensive to parse and only marginally useful for tool selection. That detail does help interpret ranked output given there is no output schema, so it earns partial rather than zero credit.

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 17-parameter search tool with no output schema, the description still covers result contents (strengths, complaints, indicative price, okstays.com link), page size and ordering, and the name-lookup override. Missing only pagination ceiling and explicit guidance on which sibling to call for follow-up detail, both of which the schema or siblings partly supply.

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%, so all 17 parameters are already documented, and the description mostly re-lists them (travel style, 8+ signals, price, minimum score, neighbourhood, distance, property_type). It does add one cross-parameter insight — that the long-stays persona defaults to property_type 'any' — but that is also repeated in 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+resource ('search hotels in a destination') plus the two distinct entry modes (destination browse vs. lookup by hotel_name), which lets an agent separate it from get_hotel, compare_hotels and find_similar_hotels without opening a schema. The scope exclusion ('Places to stay only, not flights or car hire') further sharpens what it does.

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?

The opening clause gives a concrete trigger with a worked example ('quiet hotels in Bangkok under $150') and covers the by-name variant. It does not state when to prefer siblings like get_city_overview or plan_trip, and the only exclusion is the flights/car-hire line, so routing is clear but not fully comparative.

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