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

Annotations already mark the tool as read-only and idempotent, and the description adds substantial behavioral context: prices are cached, not live; not_found does not mean unavailable; party_match=false means the price is the 2-adult reference; and prices are package totals, not per-person. No contradiction with annotations exists.

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 description is long but every sentence earns its place: it front-loads the core comparison purpose and then layers essential caveats about cache behavior, not_found handling, package totals, party matching, and date scoping. The structure supports both initial selection and correct result interpretation.

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 no output schema, the description compensates by listing key output elements: cached price, party_match, cached_at, stars, zone, board, room, features, and booking link. It also covers edge behaviors like not_found and the date-price association, making the tool safe to invoke and interpret correctly.

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?

Although the input schema covers all parameters, the description adds critical meaning beyond the schema: it defines the 'party' concept, explains party_match=false, clarifies that prices are not per-person, and insists that a price belongs only to its own date. This directly improves correct interpretation of date, adults, and children_ages.

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?

The description opens with 'Side-by-side comparison of 2-6 named hotels for a date and party' and then enumerates the exact output fields, so the tool's purpose is immediate and specific. It also explicitly distinguishes itself from 'several charter_hotel calls', which separates it from its siblings.

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 description explicitly names charter_hotel as the alternative and frames compare_hotels as the one-call replacement for comparing multiple hotels. It also gives clear cautions about cached vs. live data, not_found semantics, and the instruction to never present one date's price as another date's price.

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