Korean Law MCP Server

Overview Schema Source Related Servers Discussions Admin

get_legal_document

Read-onlyIdempotent

Retrieve Korean legal documents by ID or MST, including article-level text and paginated content across statutes, administrative rules, ordinances, precedents, and decisions.

Instructions

Retrieve a legal document. Use exactly one of document_id or mst. eflaw MST requires its YYYYMMDD effective_date from search; ID always selects current law. article is a six-digit JO code for law/eflaw (000200=Article 2, 001002=10-2). content is a slice of serialized upstream JSON, not necessarily valid JSON alone. Continue at next_offset when truncated; hashes must match across slices.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target": "<target>"
    },
    "name": "get_legal_document"
  }
}

Input Schema

Name	Required	Description	Default
`mst`	No
`offset`	No
`target`	Yes
`article`	No
`max_chars`	No
`document_id`	No
`effective_date`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Oct 31, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds real operational context on top: output is a sliced serialized upstream JSON payload that may not parse standalone, truncation is signaled by next_offset, and slice hashes must match. It does not explain what 'hashes must match' refers to in practice or what happens on an invalid/missing ID.

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?

Five tight sentences, zero filler, with the mutually-exclusive-ID rule front-loaded and the pagination caveats at the end where they are needed. Every clause adds information an agent would otherwise have to guess.

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 complex 7-parameter tool spanning eight document types with offset-based slicing, the description covers the risky parts (mode selection, date requirement, article encoding, truncation). An output schema exists so return-shape explanation is unnecessary, but the unexplained target enum and max_chars leave a gap an agent would hit on first call.

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?

With 0% schema description coverage the description must carry the load, and it does well for document_id/mst exclusivity, the effective_date requirement for eflaw MST, and the six-digit JO article format with two worked examples. However, the required 'target' parameter's eight enum values are never explained, and max_chars is unmentioned, leaving the most important discriminator undocumented.

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

Purpose4/5

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

States a specific verb and resource ('Retrieve a legal document') and covers the target families (law/eflaw) plus the two lookup modes. It distinguishes itself from search only indirectly, via 'MST requires its YYYYMMDD effective_date from search', without naming search_legal_documents as the sibling to use for discovery.

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?

Gives a concrete selection rule ('Use exactly one of document_id or mst') and contrasts the two modes: an ID always resolves to the current law while MST pulls a dated snapshot. The implication that IDs come from the search sibling is clear but not stated as an explicit 'search first' instruction or exclusion.

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

Deploy Server