dongguk-rule-mcp

lookup_dongguk_rule

Read-onlyIdempotent

Search and retrieve Dongguk University regulations using natural language queries or keywords. Get the latest official text, related clauses, and tables in one lookup.

Instructions

동국대학교 규정 질문의 기본·우선 도구. 자연어 query 또는 짧은 rule_keyword를 받아 규정 검색→최신 원문 HWP→관련 조문·별표(금액표 포함)를 한 번에 반환합니다. 근거가 충분하면 중복 조회를 생략하세요. partial·모호한 후보·적용범위 미확인 시 추가 확인이 필요합니다.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	No	전체 자연어 질문. 예: 대전 출장 여비규정의 최신 개정일, 철도운임, 일비, 숙박비를 알려줘
`terms`	No	찾을 핵심 명사. 쉼표로 구분. query에 핵심 명사가 있으면 생략 가능. 예: 국내, 철도운임, 숙박비, 일비
`campus`	No	업무 캠퍼스 맥락 all/seoul/wise. 공식 목록에는 캠퍼스 필터가 없어 전체 검색 후 적용범위를 확인합니다.	all
`law_id`	No	선택 LAW_ID. 모호한 후보를 선택한 후 직접 원문·별표 조회
`max_chars`	No	규정별 최대 반환 글자 수. 기본 12000, 최대 30000
`max_rules`	No	조회할 규정 수. 기본 1, 최대 3
`max_sections`	No	규정별 관련 블록 수. 기본 4, 최대 12
`rule_keyword`	No	선택 입력. 규정명 또는 짧은 검색어. query가 있으면 생략 가능. 예: 여비규정, 보수, 위임전결
`include_history`	No	최근 개정 연혁 5건 포함 여부

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	도구 실행 성공 여부
`data`	No	성공 시 구조화 결과
`tool`	Yes	실행한 도구 이름
`error`	No	실패 시 구조화 오류

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.10.0Sep 9, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations declare readOnlyHint and idempotentHint, and the description mentions no side effects or destructive actions, so it is consistent. However, it does not add extra behavioral details beyond the annotations, which is acceptable given the lower bar for annotated tools.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, consisting of two sentences that clearly convey the tool's purpose and usage guidance. It is well-structured and avoids unnecessary detail, making it easy for an agent to grasp quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema is available and the description mentions returning articles and annexes (including amount tables), the core behavior is covered. It also includes guidance on when to perform additional checks, making it fairly complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 9 parameters have schema descriptions with 100% coverage, including defaults and examples. The tool description itself does not add further meaning to parameters, but the existing schema documentation is sufficient, so a baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it is the primary tool for Dongguk University regulation questions, taking natural language queries or keywords and returning search results with original text and annexes. The verb 'return' and resource specification make the purpose unambiguous, distinguishing it as a high-level search tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to skip duplicate queries ('if basis is sufficient, omit duplicate queries') and when additional verification is needed (partial, ambiguous candidates, or unconfirmed applicability). This gives clear usage context, though it doesn't explicitly name sibling alternatives.

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

Deploy Server