Two tools with well-structured schemas and comprehensive parameter descriptions. koneps_search has detailed, LLM-optimized descriptions (50-200 char range) and proper enum constraints for service/business_type. Input validation is explicit (regex patterns, min/max bounds). However, output schema is not documented, the tool returns dict[str, Any] with no field specification. koneps_coverage lacks visible implementation details. Both tools are read-only and properly annotated. Missing: output schema documentation, error handling guidance, and recovery instructions.
서비스·업무구분 조합 지원 여부를 조회한다.
나라장터 공개 API 를 업무구분별로 조회한다. 물품·용역에 한정되지 않는다. 공사·외자·기타공고, 사전규격, 조달요청, 계약과정통합, 누리장터 민간입찰까지 같은 인터페이스로 조회한다. 서비스마다 지원하는 업무구분이 다르므로 잘못된 조합은 호출 전에 막는다. 어떤 조합이 가능한지는 ``koneps_coverage`` 로 확인하세요.
Output schema not documented. koneps_search returns dict[str, Any] with no field specification. LLMs cannot plan downstream operations or extract required fields without knowing response structure.
No error handling guidance. Tools do not document failure modes, retryability, or recovery steps. LLMs receive raw errors with no actionable next steps.
koneps_coverage description is minimal (13 chars). Does not explain when to call it, what it returns, or how it relates to koneps_search.
Result limiting not enforced. koneps_search accepts max_pages=10 with num_of_rows=100, potentially returning 1000 rows. No guidance on pagination or result truncation for context window management.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 46 | 2026-07-28+ | v2 |
STDIO transport only. Server is not remotely accessible and cannot be used by hosted MCP clients. Limits deployment scenarios.