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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds material context beyond them: bag choices are passed to book_trip and are editable on the booking page, bags and seats cannot be added after booking, and prices are as-listed-now snapshots with the total shown at booking. That is exactly the kind of downstream-effect and price-volatility disclosure annotations cannot carry.

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-loaded with the trigger condition and entirely free of filler, but the middle clause is a long comma-chained parenthetical enumerating return fields that is harder to parse than it needs to be. Dense and purposeful, though not maximally scannable.

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?

There is no output schema, so the description must carry the return shape — and it does, naming fare inclusions, per-choice bag details (choice_id, passenger position, direction, price, maximum), and per-flight seat counts plus price range. Combined with the workflow and timing caveats, nothing an agent needs to call or interpret 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?

Only one parameter and schema coverage is 100%, so the schema already documents offerId and its origin in search_trips; the description restates rather than extends that. The richer detail about choice_id, passenger position and quantity applies to book_trip's input, not this tool's, so it adds little parameter meaning here.

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 resource (fare inclusions, extra bags on sale, seat availability and price range for a given flight offer) with a clear source (an offerId from search_trips) and distinguishes itself from seat selection, which it explicitly routes elsewhere. An agent can separate it from search_trips, book_trip and get_offer without opening any schema.

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 triggers ('when the traveller asks about luggage or seats, or before book_trip if they want an extra bag') and an explicit negative case ('Seats are chosen by the traveller on the booking page, from the seat map, never here'). It also names the downstream tool (book_trip with extras: [{ choice_id, quantity }]) that consumes the output.

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