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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), but the description adds genuinely non-obvious behavior: a 10–30 second latency expectation, 15-minute result caching, and the ability to change filters without triggering a new search. That is meaningful operational context beyond the structured fields, though it omits anything about rate limits or failure modes on no-results.

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 purpose, then usage routing, then return shape and caching in a single dense paragraph with no filler sentences. It is on the long side and could be broken up, but every clause carries distinct information.

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 describing the response structure (summary of min price / direct / with-baggage / fastest, plus variants each carrying offer_id) and the caching/change-filters behavior. Combined with the readOnly annotation, an agent has everything needed to invoke and interpret this call.

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 description coverage is 89% across 18 parameters, so the schema already documents nearly every field (dates, pax counts, stops, transfer exclusions, time windows). The description does not add format or semantic detail beyond that, so the baseline of 3 is 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 ('Живой поиск LastBilet на конкретные даты') and frames it as the live search form for fixed dates, which immediately separates it from calendar/price-comparison siblings. The description also enumerates the richness of offers returned (baggage, transfers, payment), so an agent knows exactly what class of operation this is.

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?

Explicitly gives the when-to-use condition ('когда известны даты') and names the two alternatives for flexible dates ('для «когда дешевле» и гибких дат сначала price_calendar или cheapest_prices'). It even routes the agent forward to get_booking_link for the resulting offer_id, leaving nothing to inference.

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