City and airport codes

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is free; the description still adds real value by disclosing return-field semantics — `code`, `train`/`flight` booleans, and `whole_city` rows whose code ends in ALL. It stops short of describing result volume, ordering or empty-result behavior, which is the only remaining behavioral gap.

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 core action, then the sequencing rule, then return-field semantics — a sensible priority order with no filler. The parenthetical "a tiny train stop may have no buses" and the ALL-code note are dense but each carries non-obvious 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 and only three optional parameters, the description supplies what an agent actually needs: how to query, which field to propagate, how to interpret the flags, and the international branch. The only minor omission is that it never mentions whether codes also feed al_stays or al_hotels, which is peripheral to calling the tool 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 baseline is 3, but the description goes beyond the schema by tying international=true to a concrete consumer (al_flights_international) and giving world-city examples, and by clarifying that bus codes reuse the train codes. It does not expand on `limit` or query matching rules, which the schema already handles.

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 — look up city codes and what is sold per city — with concrete examples (THR for Tehran, MHD for Mashhad). It is unmistakably the code-resolution tool, distinct from al_trains, al_buses and al_flights which consume its output.

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?

"Use first when the user names a city" gives an explicit trigger, and it names the downstream alternatives (al_trains, al_buses, al_flights) plus the international case that feeds al_flights_international. A branch condition (international=true) is spelled out rather than implied.

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