First and last bus

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely new behavioral context: for Taipei, New Taipei and Tainan the answer is computed from the timetable because no published first/last list exists, which tells the agent the values may be derived rather than authoritative. It does not mention caching, coverage gaps for other cities, or failure behavior when no service runs that day.

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?

Three compact sentences: output definition first, then the important caveat about derived data, then concrete invocations. Nothing is redundant and the most decision-relevant fact is front-loaded.

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, the description carries some burden for describing the response, and it only says results are per direction and sub-route without indicating the shape (e.g. a list of entries with route, direction, sub-route and time). For a four-parameter read tool with full schema coverage and safety annotations, this is adequate but leaves the return format underspecified.

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 the semantics of city, date, direction and routeName are already fully documented, including the InterCity pseudo-city. The description's examples reinforce the InterCity pairing but add little beyond the schema, so the baseline 3 applies.

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 outcome: the first and last departures of a route on a given day, broken down by direction and sub-route. A reader can immediately tell this is a schedule-summary tool rather than a full timetable or live-arrival tool. It never names bus_timetable or bus_stop_arrivals as the alternative, so sibling differentiation is left implicit.

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 two worked examples (Taichung/300 and InterCity/1610) show how to combine city and routeName, and the note that Taipei, New Taipei and Tainan have no published list implies when the derived result matters. However, there is no explicit statement of when to call this instead of bus_timetable, or that routeName must be resolved first via bus_route_search (the schema says this, not the description).

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