cheapest_destinationsНаправления из города по возрастанию цены билета, при желании — в пределах бюджета («куда уехать из Казани до 1000 ₽»). С ценой километра каждого варианта.
| Name | Required | Description | Default |
|---|---|---|---|
| from | Yes | Город: русское название («Москва») или слаг (moskva) | |
| limit | No | ||
| max_price_rub | No | Бюджет в рублях |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are given, so the description carries the full burden. It discloses sorting behavior, the optional budget filter, and the inclusion of price per kilometer. However, it does not mention limit defaults, output format, or error behavior, leaving a moderate transparency 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?
The description is a single, compact sentence with an illustrative example. It front-loads the core behavior and avoids unnecessary details, though it could arguably be a bit more structured.
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 simple three-parameter tool with no output schema, the description covers the primary return values: destinations, ticket prices, and price per kilometer. Missing details such as the default result limit and whether max_price_rub is inclusive are minor but prevent a perfect score.
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?
The schema already describes 'from' and 'max_price_rub'. The description adds context for these by restating the budget filter and giving an example, but the 'limit' parameter has no schema description and is also not explained in the tool description. With 67% schema coverage, this leaves a noticeable gap.
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?
The description clearly states that the tool returns destinations from a city ordered by ascending ticket price, optionally within a budget, and includes price per kilometer. It identifies the resource and operation well, though it uses a noun phrase rather than an explicit imperative verb. It is distinct enough from siblings like get_route and search_routes.
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?
The description provides a concrete example ('куда уехать из Казани до 1000 ₽'), which clearly suggests when to use the tool: when the user wants cheap destinations from a city, possibly under a budget. It does not explicitly exclude alternatives, but the intended context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools overlap: search_routes and cheapest_destinations both list destinations from a city with price information, and city_departures/get_route both touch schedule details. The other tools are more distinct, but the listing-style tools create some ambiguity despite helpful descriptions.
Five tools follow a clear verb_noun pattern (get_distance, get_route, get_station, find_transfer, search_routes), but cheapest_destinations, city_departures, and price_per_km_stats are descriptive noun phrases. The naming is readable and consistently snake_case, but the verb convention is not uniform.
Eight tools is well-scoped for a bus travel information server. Each tool contributes a meaningful capability around routes, pricing, transfers, stations, or statistics, without feeling bloated or overly thin.
The set covers the core traveler workflow: searching routes, finding cheap options, getting detailed schedules, handling transfers, checking distances, looking up stations, and comparing price statistics. Minor gaps exist, such as no arrival-focused query or direct city-pair comparison beyond route lookup, but they are workable.