[인천공항 대중교통] 인천공항 여객터미널 택시 출차 현황 (대기수·대기시간·승차장).
1분 단위 실시간. 지역별(서울/인천/경기/인터내셔널/우등/밴) 대기 택시 수와 대기시간.
Args:
terminal: "T1" / "T2" / "P01" / "P03". 기본 T1.
lang: "ko"/"en".
Returns:
{terminal, status, update_time, regions: {서울/인천/경기/인터내셔널/우등/밴: {cnt, wait_time, stand}}}
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ko | |
| terminal | No | T1 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations: it mentions real-time updates (1-minute intervals) and specifies the returned data structure (terminal, status, update_time, regions). Annotations already indicate readOnly, idempotent, and non-destructive behavior, so the description complements without contradiction.
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 well-structured: a brief title line, a line about update frequency, then a clear Args section with parameter details, and a Returns section showing the output format. It is concise yet informative, though slightly verbose with the Korean formatting.
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?
Given the tool has only 2 parameters (both with defaults), rich annotations, and an output schema, the description covers all essential aspects: purpose, update frequency, parameter semantics, and return structure. No significant gaps remain for an agent to use this tool correctly.
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?
The input schema has no description coverage (0%), but the tool description provides explicit meanings and allowed values for both parameters: terminal can be 'T1', 'T2', 'P01', or 'P03' with default 'T1', and lang can be 'ko' or 'en'. This significantly compensates for the schema's lack of descriptions.
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 clearly states the tool returns taxi departure status at Incheon Airport passenger terminals, including waiting count, waiting time, and boarding area. The verb '조회' (inquiry) is implied, and the resource is unambiguously taxi-related. It does not explicitly distinguish from sibling tools like airport_bus, but the focus on taxi is clear.
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 notes real-time updates (1-minute intervals) but does not provide explicit guidance on when to use this tool versus alternatives like airport_bus or airport_train. Usage context is implied by the domain (taxi) but lacks when-not or alternative suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool addresses a distinct mode of transit (bus, shuttle real-time, shuttle schedule, taxi, train) with clear descriptions, leaving no ambiguity for an agent.
All tool names follow a consistent `airport_<transport_type>` pattern, with shuttle tools further differentiated by `_next` and `_schedule` suffixes, making them predictable.
With 5 tools covering bus, shuttle (real-time and schedule), taxi, and train, the count is well-scoped for an airport transit information server.
The tool set covers all major transit modes to/from and within Incheon Airport, including real-time and schedule data, with no obvious gaps.