결정례·해석례 찾기

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so safety is covered. The description adds real behavioral context: it is a single federated search across four heterogeneous corpora, and results carry source and id fields suitable for hand-off to read_ruling. It does not mention result limits, ranking, or what an empty result means.

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?

Two short sentences with the main action front-loaded and the follow-up instruction at the end. The parenthetical court=/constitutional=/tribunal=/moleg= mapping duplicates the sources parameter's enum description verbatim, which is the only wasted text.

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?

There is no output schema, so the description must carry return-value information, and it only tells us results expose source and id. It says nothing about result shape beyond that, whether perSource caps results per corpus or overall, or how to interpret a query that matches nothing in one source.

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 coverage is 75%, just under the threshold where the schema alone would suffice. The parenthetical source mapping merely restates the sources field's own enum description, adding no new meaning, and perSource (1–30, default 5) has no description anywhere, so its per-source semantics are left unstated. The query example lives in the schema, not the description.

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 (검색) and enumerates the four ruling resources covered (법원 판례, 헌재 결정, 조세심판원 심판례, 법제처 해석례), which implicitly separates it from statute-oriented siblings like find_statute and read_provision. It also names read_ruling as the downstream tool. It does not explicitly contrast with find_statute or find_admin_rule, so differentiation is inferred rather than declared.

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?

"결과의 source/id를 read_ruling에 넘기세요" gives an explicit chaining instruction to the follow-up tool, so the agent knows this is the discovery step and read_ruling is the retrieval step. What's missing is a negative case (when to use find_statute or find_admin_rule instead) and any statement that the four source values can be mixed or narrowed per query.

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