legal_analysis

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

Annotations already declare readOnly/idempotent/openWorld, and the description layers real behavioral detail on top: external DB cross-verification, distinguishing 실존불가 vs 미확인, detecting 변경·폐기 of cited cases, returning the version of a law in force at a date including 부칙 경과조치, and emitting a mermaid reverse-citation graph. This tells the agent what actually happens and how results are shaped.

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?

Front-loaded with the tool name and a one-line summary ('검증·분석 4종 통합'), then a compact pipe-delimited breakdown per mode. It is dense but each clause carries mode-specific content; only minor redundancy with the schema keeps it from a 5.

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?

For a complex 4-mode, 11-parameter tool with no output schema, the description covers each mode's behavior, required inputs, and the shape of key outputs (mermaid graph, change/obsolete detection, distinct existence verdicts). Some mode-level return-format detail is left implicit, but it is sufficient for an agent to invoke the tool correctly.

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 the schema already documents all 11 parameters, and the description's per-parameter notes (jo accepting '제103조'/'103조'/6-digit JO codes, lawName accepting abbreviations and administrative rules) largely restate the schema. It does consolidate which parameters are required per mode, which adds some navigational value, so baseline 3 is appropriate.

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 names the resource (Korean-law verification/analysis) and enumerates four distinct modes, each with a specific verb+resource: cross-verifying citations against the 법제처 DB, checking whether a case is still good law, resolving the law version in force at a date, and building a reverse citation graph. An agent can tell this apart from siblings like get_law_text or search_law without opening the schema.

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?

Each mode carries its own triggering condition and required inputs (e.g., verify_citations for LLM hallucination checking, cite_check for a case-number 'Citator', applicable_law for 행위시법 timing), so the agent knows which mode to pick. It stops short of explicitly routing to sibling tools for the cases this tool does not cover, so it is clear context without exclusions.

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