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

Annotations only indicate read-only and idempotent behavior, but the description adds major behavioral nuance: the data is cached, not live; party_match semantics; exact_date_matches vs other_cached_offers; that prices are package totals in EUR, not per-person; and that a price belongs only to its own date. This far exceeds what the annotations reveal and prevents common misinterpretations.

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 dense and packed with necessary caveats, all of which earn their place. It could be better organized with bullet points, and there is minor repetition of the not-live/cached concept, but it remains well-structured with front-loaded scope and clear separators between key ideas.

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 supplies the crucial output semantics: exact_date_matches, other_cached_offers, availability_status=reference_other_date, party_match flags, cached_at/age_minutes, and the hotel_page fallback. It also covers edge cases (no cached date, wrong party, wrong date) so an agent can correctly interpret and present results in every scenario.

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 the baseline is 3. The description adds value by instructing the agent to always pass the date and party given by the user, explaining that the exact party's cache is read first, and clarifying the 2-adult reference fallback. This behavioral mapping goes beyond the schema's per-field descriptions, though it is somewhat redundant with them.

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 states a specific verb and scope: it returns cached prices for ONE named hotel, and gives an example hotel name. It explicitly distinguishes itself from the siblings charter_offers (filters), compare_hotels (2-6 named hotels), and hotel_details (amenities), so an agent can immediately differentiate it.

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 gives explicit when-to-use guidance: call it when the user names one specific hotel, and do NOT call it repeatedly for browsing — instead use charter_offers or compare_hotels. It also prescribes a specific fallback behavior when nothing is cached: say so and provide hotel_page, which leaves no ambiguity.

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