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

With no annotations, the description carries the full burden, and it does add real behavioral context: date defaults to Taipei's current date, station inputs may be names or codes, and the 24:00–29:59 convention marks post-midnight departures of the operating day. It says nothing about what the response contains (all trains that day? a windowed slice?), ordering, or result size, which is a notable gap for a read with no output schema.

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?

Highly compressed but front-loaded: the core action and resource come first, then the parameter conventions in short semicolon clauses. The trailing English sentence is a bilingual echo rather than new content, but it costs little and the whole definition stays under two lines while covering every parameter.

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 4-parameter lookup with no annotations and no output schema, the description covers the call side adequately — inputs, defaults, and the unusual time convention are all addressed. What is missing is return-side context: whether the result is a full-day train list, whether times/train numbers/fares are included, and how a partial-day `time` filters the list.

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 only 25% (just `time`), so the description must compensate, and it does: it clarifies that origin/destination accept either station names or codes, that date is optional and defaults to today in Taipei, and that time is HH:mm with the extended-hours convention. These are the semantics the bare schema lacks; only the departure-window meaning of `time` relative to a returned timetable is left implicit.

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: '查高鐵某日起迄站時刻' (query THSR timetable for an origin/destination pair on a date), and the THSR label implicitly separates it from tra_timetable. It does not explicitly name the sibling, so differentiation is left to the agent's knowledge of the rail systems.

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?

Usage is implied by 'THSR OD timetable' but there is no explicit when-to-use or when-not guidance, and no pointer telling the agent to use tra_timetable for conventional rail or tra_live for real-time positions. For an agent choosing among eight scheduling siblings, that omission matters.

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