Metro next trains

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

Annotations cover read-only and open-world safety, so the bar is lower, and the description adds real value on top: the per-system result semantics and the warning that an empty TRTC response is normal behaviour rather than failure. It does not discuss rate limits, caching, or coverage gaps for stations without service.

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 tight sentences, front-loaded with the return content, then the caveat that prevents misreading empty results, then an example. Nothing is redundant and nothing is buried.

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 must convey what comes back, and it does: minutes until next trains, per line and destination, plus the system-dependent variance. Minor gaps remain around whether multiple upcoming trains are returned per destination and how stations without service appear.

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% and the enum already spells out all four system codes with Chinese and English names, so the schema carries the parameter burden. The worked example (system "KRTC", station "美麗島") usefully signals that station values are local-language names, but that is the only addition beyond structured fields. 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?

Opens with a specific verb+resource: minutes until the next metro trains, broken down per line and destination. That is clearly distinct from timetable/fare siblings in the list, but the near-neighbour metro_first_last_train is never named or contrasted, so the 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?

Explains the operational condition that matters most: which systems return full station lists and that TRTC returns only imminent arrivals, so an empty Taipei board is expected, not an error. It also gives a concrete call example. It stops short of naming alternatives such as metro_first_last_train for first/last departure queries.

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