Re-check offer

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

Annotations already cover read-only/idempotent/non-destructive/open-world, yet the description adds substantial behavior the annotations cannot: a fresh search is always performed (never the replay cache), a price_cap is intentionally omitted with breaks surfaced in filter_violations, and critically that check_failed means the check did not run rather than the offer being gone. It also disclaims that this is not a booking guarantee.

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?

Dense and front-loaded, with the core action and the freshness constraint stated first. Every sentence carries information, though the middle clauses are telegraphic and would benefit from slightly clearer separation.

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?

An output schema exists, so return values need not be re-explained; the description instead supplies the interpretation of the check_failed outcome, which is the non-obvious part. For an 8-param tool it delegates full rules to get_guide, which is reasonable, and covers the primary call path adequately.

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 0% across 8 parameters, so the description must compensate. It richly explains the two key inputs — offer (required fields: price plus each segment's flight_number, origin, destination, departure clock) and query (defaults to the offer's evidence query, replayed with cabin/stops/bags/airline filters) — but leaves fetch, proxy, country, currency, allow_substitute, and allow_loose_match entirely undocumented.

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 (re-check) and resource (an earlier flight offer) with a precise scope: one fresh Google Flights search, never the replay cache. This cleanly distinguishes it from search_flights, which the description explicitly references as the source of the offer being re-checked.

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?

Establishes the context of use (re-validating a prior search_flights offer) and what input qualifies as an offer, including the minimum fields needed. It does not name a sibling to use instead for other scenarios, but the 'earlier offer' framing makes the triggering condition clear.

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