research_issue

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds genuinely useful behavior beyond them: the LAW_OC dependency (article text is omitted and only interpretations/basic rules are returned without it) and the 10–30 second latency. The explicit "읽기 전용" restates the annotation. Dependency and latency disclosure elevate this above baseline.

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 purpose, then the when/return/dependency/latency facts in labeled clauses (언제, 반환). Bilingual duplication and dense Korean add length, but every clause carries distinct information and the structure is scannable. Slightly heavier than ideal but no filler.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the response keys. It also documents the external dependency, latency, and read-only nature for a 6-parameter tool. What remains thin is error/failure behavior when LAW_OC is absent or the period is malformed.

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 baseline would be 3. The description adds value beyond field-level schema docs by tying the parameters into a temporal-resolution model: the reference date, whether then-vs-current article text changed, and whether each interpretation/case was registered under text matching the reference date. This conceptual framing of 'period' exceeds what the schema conveys alone.

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?

"Bundle everything that applied to an issue at a past date" names a specific verb (bundle/retrieve) and a well-defined resource (all authorities applicable to an article at a historical point). The Korean gloss enumerates the bundled categories (3-tier article text, 기본통칙, 집행기준, interpretations, cases), which also implicitly distinguishes it from the single-category siblings. It stops short of explicitly naming alternatives like basic_rules or casebook_search, so not quite a 5.

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?

"언제: 세무조사·불복처럼 특정 사업연도에 적용되는 근거를 정리할 때" gives a concrete triggering scenario (tax audit/appeal needing point-in-time authority). It explains the governing logic (fixed reference date, comparing then-vs-now article text), which is clear context. No explicit exclusions or sibling routing is provided, so it is not a full 5.

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