legal_analysis

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as safe. The description adds substantial behavioral context beyond annotations: verify_citations cross-checks against the law DB to prevent LLM hallucination; cite_check performs reverse citation tracking and detects changes/abandonment; applicable_law retrieves the correct law version with transitional provisions; impact_map generates a reverse reference graph with mermaid output. It also discloses behavior for optional parameters like deepScan (default true, skipping detection if false). No contradiction with annotations.

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 compact and information-dense, covering four modes in a single paragraph without excess verbiage. It is front-loaded with the title 'Korean-law-mcp — [정밀분석] 검증·분석 4종 통합.' However, the structure mixes Korean and English with pipe separators, which reduces scanability for an English-speaking AI agent. A bulleted or sectioned format would improve clarity without sacrificing conciseness.

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 high complexity (11 parameters, 4 modes, no output schema), the description provides adequate contextual coverage: it explains the purpose and required inputs for each mode, hints at output types (e.g., 'mermaid 그래프 코드 출력' for impact_map, '법령 버전+그 시점 조문+부칙 경과조치' for applicable_law), and details behavior like default settings. It does not fully specify return structures, but without an output schema, that is acceptable. The description could be more complete by clarifying what verify_citations returns (e.g., a list of validated citations).

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?

Schema description coverage is 100%, so baseline is 3, but the description adds significant value: it groups parameters by mode, specifies which parameters are required for each mode (using '필수' markers), provides clear examples (e.g., '제103조', '2023-05-10', '2013다61381'), and explains defaults (e.g., '기본 15' for maxCitations, '기본 true' for deepScan). This meaningfully enriches the bare schema 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 explicitly states it is an integrated verification/analysis tool for Korean law with four distinct modes (verify_citations, cite_check, applicable_law, impact_map), each with a specific verb and resource (e.g., '검증·분석 4종 통합' and 'mode: verify_citations=텍스트 속 조문 인용...이 실존하는지 법제처 DB 교차검증'). This clearly distinguishes it from sibling tools like search_law or get_law_text, which are for retrieval, not analysis.

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 provides clear usage context by specifying required parameters per mode (e.g., 'text 필수' for verify_citations, 'caseNumber 필수' for cite_check, 'lawName+date 필수' for applicable_law, 'lawName+jo 필수' for impact_map). It implies when each mode is appropriate but does not explicitly state when not to use this tool or list alternatives (e.g., using get_law_text for plain text retrieval). However, the mode selection paradigm effectively guides the agent.

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