Search buses

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

Annotations already declare readOnly/idempotent/openWorld, so the description's job is added context — and it delivers: price_toman is charged once per seat, refund_penalties apply to every bus unless overridden, and the until_hours_before / free_cancel_minutes semantics are spelled out, including that null means up to departure. That is genuine behavior an agent could not infer from the 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-loads the purpose, then the id semantics, then the pricing/refund rules, then next-step routing — a sensible order with no filler. The refund-penalty sentence is dense and reads as a spec dump, which costs it the top mark.

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?

For a 10-parameter search tool with a full schema and an output schema, the description covers the id-type rule, the money and cancellation semantics, and the follow-up calls, so an agent has everything needed to call it and interpret results. Return-value explanation is not required since an output schema exists.

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 100%, so baseline is 3; the description adds real meaning on top by explaining that a city id covers all its terminals while a terminal id covers only that one — a non-obvious distinction for origin/destination. The per-seat pricing and refund-penalty notes describe output fields rather than input parameters, so it does not go further than a 4.

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 ('Intercity buses on a date') and enumerates the returned attributes (company, terminal, times, price, free seats, bus type, stops, refund penalties). The resource noun 'buses' cleanly separates it from mb_search_flights, mb_search_trains, and mb_search_taxis.

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 the agent forward: 'Next: mb_bus_seats with a bus_id for seat numbers and women/men seats; other days: mb_bus_price_calendar.' That covers the two most likely adjacent needs, but it never says when NOT to use this tool (e.g. vs mb_alternative_routes) or that ids must come from mb_find_place.

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