정기공시 이행 점검 (제출 여부·지연·미제출)

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

No annotations exist, so the description carries the full burden and does so well: 80-company-per-call limit, one lookup per company, EGROUP_API_KEY requirement for group audit, non_filing_is_signal:false for J009, due:false suppression of non-filing verdicts, ambiguous_assignment/possibly_filed_late flags, representative-company non-substitution rule, and the annual May-1 snapshot caveat. It also warns that non-filing candidates are not definitive.

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 core purpose in the first sentence, then a tight bullet list of behaviors and caveats. It is long, but nearly every bullet carries a distinct constraint or edge case rather than restating the schema.

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 and no annotations, the description supplies the return shape (on_time / late_candidates / not_filed_candidates per company), the flag semantics, and the scope_caveats bucket. A few finer points (exact per-company record fields, scope_caveats structure) remain implicit, but an agent has enough to call and interpret it.

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; the description adds genuine meaning by explaining why year_month defaults to the inspection year's May (the portal snapshot is taken each May 1, so using the latest snapshot for past years misaligns the population), the group/companies mutual exclusion, and the duties default behavior.

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 (점검/audit) and resource (정기공시, specifically 기업집단현황 J004 and 하도급대금 결제조건 J009) and the exact dimensions checked (제출 여부·지연·미제출). The scope is unusually precise, but it never names a sibling such as audit_group_disclosures or check_disclosure_duty to draw the boundary explicitly.

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 usage context: it audits submission/timeliness only and explicitly excludes content accuracy ('내용의 정확성은 보지 않습니다'), and it flags that group-level auditing needs EGROUP_API_KEY. It does not point to an alternative tool for the cases it declines (content correctness), so it stops short of explicit when-not routing.

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