get_urban_station_info

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

Annotations are absent, so the description carries the full burden — and it delivers richly. It discloses the KRIC data source with a modification date, prescribes tone based on data age (recent vs old), restricts phone-number disclosure to explicit requests or emergency/safety cases, defines multi-dataset handling (oldest date, single notice), and imposes an explicit anti-fabrication policy for empty results. This is far beyond what annotations would provide.

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?

Purpose is front-loaded in the first line, followed by parameter definitions, then the guidance block. The Korean text is verbose, but the guidance block is dense with actionable, specific rules (freshness tone, phone-number policy, no-repeat rule) rather than filler. Every section earns its place, though the answer-guidance could be tightened.

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 an output schema present, return-value explanation is unnecessary. The description covers purpose, both parameters, and behavioral rules thoroughly. The main gaps are the lack of explicit sibling routing and the operator value format, but for a 2-parameter, 1-required tool with an output schema, the definition is substantially complete.

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 0%, so the description must compensate, and it does: station_name is defined as 역명 and operator as '환승역 구분용 운영기관 코드/명 (선택)' — adding real meaning to the bare string schema, especially for the otherwise cryptic operator parameter. It could specify the operator value format more precisely, but both parameters receive coverage.

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?

Opening line states a specific verb+resource: '도시철도 역사 기본정보 조회' (retrieve urban railway station basic info) with the scoping fields (주소·좌표·다국어 역명). This clearly differentiates from sibling tools that cover specific aspects like transfer info (get_urban_transfer_info), platforms (get_urban_platform), or exits (get_urban_exit_info).

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 contains no explicit when-to-use guidance or named alternatives. The operator parameter note ('환승역 구분용') implies a transfer-station distinction from get_urban_transfer_info, but the agent is never told which of the many sibling station tools to prefer and when. The [답변 지침] block governs answer tone, not tool selection. Usage context is only implied by the purpose.

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