law_body

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

Even with readOnlyHint=true in annotations, the description discloses several non-obvious behaviors: calling without ef_date returns HTML rather than an error, max_chars truncates the body and notifies the caller, and the parameter-name normalization (MST/ID) is handled internally. These are exact, actionable traits that an agent would otherwise only discover by running the tool.

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?

A one-sentence summary followed by a tight bulleted argument list. Every bullet provides real information, the 🔴 emoji highlights the critical ef_date pitfall, and there is no filler. The structure is easy to scan and front-loads the most important facts.

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?

The description is nearly complete for invocation: all parameters are explained, edge cases are flagged, and the read-only behavior is implicit. It lacks a clear statement of the return format (HTML vs JSON) and does not explicitly instruct the agent to use law_targets for target codes, which are the main remaining gaps given there is no output schema.

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 0%, so the description carries the full burden. It explains all five params with roles and conditions, including the ef_date warning and the include_articles scope. The only notable gap is target, which is simply 'branch code' with no enumeration or pointer to law_targets, leaving possible valid values unresolved.

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 is clear and specific: it retrieves the body (본문) of a single identifier, listing example content types (조문, 판시사항, 질의요지). The singular '1건' and the verb '받는다' establish a distinct action from siblings like law_search, law_collect, or law_status. No ambiguity about the core purpose.

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 gives strong conditional context for when parameters apply: doc_id is described as a 'list result' serial number, ef_date is 'eflaw 전용', and include_articles is restricted to laws/autonomous regulations. However, it never explicitly names alternative tools or says when not to use this tool, so it lacks the full when/when-not guidance of a 5.

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