get_law_text

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

Annotations already declare readOnly/idempotent/openWorld, so the description's real value is behavioral detail: the server normalizes natural-language jo input, and an efYd that isn't a real enforcement date returns NOT_FOUND rather than silently failing. That error semantics and input-normalization disclosure is more than annotations provide, though return format/pagination behavior is unaddressed.

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 tool identity and purpose, then parameter rules, then the efYd caveat; no filler sentences. The 6-digit JO-code example duplicates the schema description, costing a little efficiency.

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 read-only retrieval tool with no output schema, the description covers what the agent needs to pick arguments: obligation of mst/lawId, jo granularity, and the current-vs-scheduled-version decision. It leaves the mst/lawId exclusivity rule and any paging behavior implicit.

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%, and the description largely restates the jo encoding rule already spelled out in the schema, so baseline 3 applies. It does add one piece of semantic information not in the schema — that mst or lawId must effectively be supplied despite required being empty — but that tension is left unclarified rather than explained.

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?

States a specific verb+resource: full-text retrieval of statutory articles ([법령조회] 조문 전문 조회), with the optional narrowing to a single article via jo. It implicitly distinguishes itself from search_law by telling the agent to obtain mst/lawId there, though it never explicitly contrasts with get_annexes or legal_research.

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?

Gives concrete selection rules: mst/lawId are needed, jo is only for pinning a single article, use no efYd for the current text, and use the efYd that search_law reported for a forthcoming version. It stops short of explicit when-not-use-this guidance or sibling routing beyond search_law.

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