lawmadi-os

by io.github.peter120525-cmd

lookup_precedent

[NO KEY · preview depth, 1/day] 사건번호로 한국 판례를 조회합니다. 먼저 검증 자산(17,954건, 전부 law.go.kr 본문 대조 완료)을 보고, 없으면 law.go.kr 정본 색인(대법원 판례·헌재결정례 전수)에서 실재를 확인한 뒤 본문을 직접 받아옵니다. 응답의 source 필드가 근거의 강도를 가릅니다 — corpus 는 본문까지 대조된 것이고, authoritative_index 는 정본에서 실재를 확인하고 본문을 그 자리에서 받아온 것입니다. 법원·선고일·사건명·판시사항·판결요지·참조조문과 law.go.kr 원문 직결 링크를 돌려줍니다. LLM을 부르지 않는 결정론적 조회라 할루시네이션이 없습니다. 입력 예: '2020도3050', '대법원 2024. 4. 16. 선고 2020도3050 판결', '2016헌마90'. / Look up a Korean court case by docket number in Lawmadi's verified-asset corpus (17,954 precedents, each confirmed against law.go.kr). Returns court, decision date, case name, holding, summary, referenced articles and a direct law.go.kr full-text link. Deterministic — no LLM, no hallucination. Callable without an API key at preview depth (metadata + law.go.kr link + first 200 chars of the holding); a key unlocks the full holding, summary and referenced articles. / 키 없이도 미리보기 깊이로 조회됩니다 — 판시사항 전문·판결요지·참조조문은 키 발급 후 제공됩니다.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`case_no`	Yes	Docket number or full citation. Example: '2020도3050'.
`client_tag`	No	선택. client_tag: 호출자 식별용, 응답에 영향 없음(8~64자, 영숫자·_-.). 서버 로그에만 남아 호출을 골라 세는 데 씁니다. 형식이 어긋나면 무시합니다 — 거절하지 않습니다. 질의 본문에 섞지 마세요: 본문에 넣으면 질문의 일부가 되어 분류와 검증 결과가 달라집니다. / Optional caller label (8-64 chars). Logged only; never affects the response. Invalid values are ignored, not rejected. Do not put it in the query text — there it becomes part of the question.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 23, 2026

addedInput schema / properties / client_tag

Added value: +{
+  "description": "선택. client_tag: 호출자 식별용, **응답에 영향 없음**(8~64자, 영숫자·_-.). 서버 로그에만 남아 호출을 골라 세는 데 씁니다. 형식이 어긋나면 무시합니다 — 거절하지 않습니다. 질의 본문에 섞지 마세요: 본문에 넣으면 질문의 일부가 되어 분류와 검증 결과가 달라집니다. / Optional caller label (8-64 chars). Logged only; never affects the response. Invalid values are ignored, not rejected. Do not put it in the query text — there it becomes part of the question.",
+  "type": "string"
+}

AddedAug 11, 2026

TDQS

A4.2/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full burden, and it does: no-LLM determinism, the 1/day preview rate limit, the 200-char holding truncation without a key, the semantics of the returned source field (corpus vs authoritative_index), and the two-tier fallback path. This is far beyond what a bare mutation/read hint would convey.

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

Conciseness3/5

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

The critical constraint (no key, preview depth) is front-loaded, but the content is delivered three times in Korean, English, and Korean again; the final Korean line re-states the no-key/key-depth split already given twice. High information density is undercut by this redundancy.

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?

For a two-parameter lookup with no output schema and no annotations, the description is nearly self-sufficient: it enumerates return fields, explains source-strength semantics, and covers key/rate-limit tiers. It stops short of stating not-found behavior when neither the corpus nor the index contains the docket.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning by showing accepted input forms — bare docket ('2020도3050'), full citation ('대법원 2024. 4. 16. 선고 2020도3050 판결'), and constitutional form ('2016헌마90') — which the schema's single example does not cover.

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?

States a specific verb and resource up front ('사건번호로 한국 판례를 조회합니다' / 'Look up a Korean court case by docket number'), and the returned artifact (court, date, case name, holding, summary, articles, link) makes it immediately distinguishable from lookup_statute and verify_citations.

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

Usage Guidelines3/5

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

It clearly describes the operational context — callable without a key at preview depth, key unlocks full holding — and the internal fallback chain (verified corpus first, then authoritative index). However, it never names or routes against siblings, so an agent must infer that lookup_statute handles statutes and verify_citations handles citation checking.

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

All lawmadi-os tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?