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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real context beyond that — the OpenDART source, default windows, exemption of corrected filings, and what each category actually contains (e.g. 위험 = 관리종목·거래정지·감사의견·횡령배임). However it never says what the response looks like or how results are capped in practice, so with annotations present this lands at adequate rather than rich.

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 the action and the not-this (정기보고서) distinction, then categories, then defaults, then query/sort hints — a sensible priority order with no filler sentences. It is dense to the point of being hard to scan, with a long parenthetical gloss block, but every clause carries information an agent needs.

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 10-parameter, zero-required, read-only search tool with no output schema, the definition covers defaults, category semantics, sort modes, and search behavior thoroughly. The remaining gap is return-value expectations — '핵심 내용과 함께' only hints that each disclosure comes with a distilled summary — and the undocumented limit cap of 200, which an agent could otherwise trip over.

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 already 80%, yet the description still adds meaning: absent-stock vs present-stock behavior for stock, how query tokenizes ('공백으로 여러 개 = 모두 포함' via schema), what min_amount measures across contract/capital/song-claim types, and semantic definitions for ambiguous categories like 실적전망, 최대주주지분, and the '(자회사)' suffix. The limit parameter is left unexplained in both schema and description, which keeps it off a 4.5+.

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 ('수시공시 찾기') and immediately scopes it against the adjacent concept '정기보고서 말고 주가에 직접 영향을 주는 공시', which tells an agent this is not a periodic-filing search. The enumerated category list and the note that content is distilled from OpenDART 원문 서식 make the resource concrete rather than generic.

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?

Gives clear invocation conditions: with a stock it defaults to that company's last 3 years, without one it scans the whole market for the last 30 days, plus example questions ('최근 대규모 수주', 'CB 발행 많이 한 회사') that map to query/min_amount/sort usage. It does not name competing siblings such as search_filings, filing, or disclosure_impact, so the agent must infer routing rather than being told explicitly.

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