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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond: it discloses the ranking heuristic (price plus penalty for long trips and extra stops), the book_link destination, the tight_connection threshold (<60 min), and the travel_time_total semantics with an explicit warning not to present it as one flight's duration. That is substantive behavioral context an agent cannot get from annotations.

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 purpose and result shape, then return-field detail, then usage guidance. It is a dense single paragraph and slightly packed with parenthetical field lists, but nearly every clause carries information; only the "Reads only; nothing is booked" line mildly restates readOnlyHint.

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?

No output schema exists, so the description carries the full burden of explaining return values, and it does: total_available, summary, per-flight outbound/return structure, duration, stops, layovers, carriers, and book_link. Combined with the travel_time_total caveat, an agent has enough to call and to report results 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?

Schema coverage is 100%, so the baseline is 3; the description adds meaning the schema does not, notably that prices are "the total price for all adults" and that omitting return yields one way. It does not elaborate on airport-code validation, but the schema already enforces that pattern.

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 ("Searches flights between two airports, round trip or one way") and immediately characterizes the result set (top 6 by value, limit up to 20). No sibling tool covers flights, so differentiation is implicit, but the scope is unambiguous.

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 routes usage: "Use after stays and tours for a built trip (get_trip's next has the dates)" names the sequencing and the sibling that supplies the dates, and "ask for the origin airport if unknown" handles the missing-input case. This is when-to-use plus a fallback, not just context.

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