get_urban_surroundings

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

With no annotations, the description assumes the burden and discloses important behavior: it details how to tailor the answer based on the data modification date in _meta, when to add warnings, and that empty results must be reported as '해당 데이터 없음' rather than fabricated. This is substantive behavioral context that an agent would not otherwise know.

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 organized into a one-line purpose, a compact parameter list, and a clearly separated answer-guidelines block. It is longer than average, but the extensive recency rule is essential and non-redundant; only a slight repetition of 'don't repeat the notice' could be trimmed.

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?

An output schema exists, so return-value documentation is not required. The description covers the unusual output behavior (geographic data freshness, tone adjustment, empty-result handling) thoroughly. Remaining gaps are minor, such as exact accepted formats for station_name and operator, but they are partially addressed in the parameter 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 description coverage is 0%, but the description manually defines all three parameters: kind with its allowed values, station_name as the station name, and operator as an optional institution code/name. It adds meaning beyond the bare schema, even though exact value formats for station_name and operator are left open.

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 opens with a specific operation '도시철도 역 주변 시설 조회' (retrieve facilities around urban railway stations) and enumerates the exact facility categories: public_transport, parking, bike_parking, bike_rental. This clearly states the resource and distinguishes it from the many other urban-* sibling tools, though it does not explicitly differentiate from close relatives like get_urban_amenity.

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?

When to use the tool is implied by the purpose and the kind parameter values: an agent should call it when a user asks about public transport, parking, or bicycle facilities near an urban station. However, there are no explicit exclusion criteria or pointers to alternative sibling tools, so the guidance is inferred rather than stated.

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