related_judge

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

With no annotations, the description carries the full burden and does substantial work: it lays out the livelihood-shared-kinsfolk test, the hierarchy of primary criteria, the presumption from same-household registration, what evidence is insufficient (진술서만은 안 됨), and the fact that 상증법 has no such category. It also discloses the return contents (결론·사유·결정·해석 번호). It does not discuss failure modes or how ambiguous inputs are reported beyond '입력 확인 필요'.

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?

Purpose, "언제", "입력", and "결과" are cleanly front-loaded, but the final sentence repeats the opening sentence almost verbatim, and the "입력" block restates parameter descriptions that are already 100% covered in the schema. Both could be cut without losing information.

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 14-parameter, nested-object tool with no output schema, the definition covers purpose, trigger conditions, per-parameter meaning, decision logic, and the shape of the returned judgment. Only the precise output format and behavior on missing required inputs remain unstated, which is a modest gap.

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 100%, so the baseline is 3, but the description earns an extra point by mapping each parameter to its role and by explaining the legal logic behind the many livelihood_shared fields rather than just naming them. The primary-criterion rules add real meaning an agent cannot infer from the schema's enum labels.

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 and resource: judge (판정한다) whether two parties are in a special relationship (특수관계) and the applicable subparagraph (호수), scoped to three named statutes (국세기본법·법인세법·상증법). That is far more specific than the name alone. It does not, however, differentiate itself from overlapping siblings such as kinship_check, related_provision_at, or extract_relations, which an agent could easily confuse it with.

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?

An explicit "언제" line gives clear context: use during tax audits or deemed-gift review to confirm a special relationship and the applicable subparagraph between two persons or entities. That satisfies 'clear context'. No when-not conditions or named alternatives are given, which is the gap keeping it from a 5 despite several candidate siblings.

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