타사 선례·문안 참고

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

No annotations are provided, so the description carries the full burden of behavioral disclosure — and it delivers richly. It discloses the correction basis (정정 반영 최종본 기준), the semantics of coverage (훑은 구간, 0건 != "그런 공시가 없다"), the selection rule (회사당 1건), and the lookback stop condition (후보가 모이면 멈춤). This is exemplary for an unannotated 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?

The core purpose is front-loaded in the first sentence, and the caveats are organized as compact bullet points. Each bullet earns its place (correction basis, coverage semantics, time range behavior). It is somewhat long for an 8-parameter tool, but the density of useful caveats justifies the length.

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 complex 8-parameter tool with no output schema and no annotations, the description covers the essential interpretation traps (coverage, 0건 meaning, final-version basis) and output format (마크다운 표 구조 보존). What's missing is minor — e.g., no explicit statement of timeouts or result count display — but these aren't critical to correct invocation.

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 adds genuine behavioral meaning beyond the schema: it clarifies that count consumes one download per precedent, explains lookback_days' non-monotonic scan behavior (후보가 모이면 더 내려가지 않으며 항상 전수로 확인), and ties coverage to interpretation of results. This elevation justifies a 4.

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 states a specific verb and resource — answering "다른 회사는 이 항목을 어떻게 썼나" by fetching recent disclosures of the same type, selecting one per company, and returning the original text as markdown. It clearly differentiates from siblings: it's for 문안 참고 (wording reference) and explicitly contrasts with 지연 판정 (delay judgment), distinguishing it from check_disclosure_duty and search_disclosures.

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?

It gives clear context on when to use it (finding third-party wording/문안), grounds the default scope (대규모내부거래 J001), and explicitly states what it is NOT for ("

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