Compare a hotel's prices across sites

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 real behavioral context beyond that: aggregation across all booking sources, cheapest-first ordering, currency conversion to INR with original currency retained, tax status, and the explicit 'Does not book' boundary. It says nothing about rate limits, caching, or failure modes for unavailable dates/rooms.

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 tight sentences, zero filler, with the output shape front-loaded before the input guidance and the non-booking boundary last. Every clause carries information an agent needs.

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 present, the description need not explain return values, yet it still outlines them for routing purposes. Combined with full schema coverage, four annotations, and the explicit scope boundary, nothing an agent needs to invoke this correctly is missing.

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 every parameter including the hotel_id-vs-name+lat/lng alternatives is already documented in the schema. The description restates the identifier options and date scoping but adds no syntax or format detail the schema lacks, making the baseline 3 appropriate.

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 (fetch current prices for one hotel across every source) plus the exact output ordering and fields (cheapest first, INR with original currency, tax status, availability, links). The phrase 'one hotel' and the explicit 'Does not book' cleanly separate it from sibling compare_hotels.

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 concrete input routing: use a hotel_id from search_hotels or plan_stays, or a name with lat/lng, and states the tool does not book. It stops short of explicitly contrasting with compare_hotels or plan_stays when a multi-hotel comparison is wanted, so the when-not case is only implied.

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