정기공시 이행 점검 (제출 여부·지연·미제출)

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

With no annotations provided, the description carries the full burden and does so extensively. It discloses that content accuracy is not checked, due:false items are ignored for non-filing, J009 has non_filing_is_signal:false, ambiguous assignments get ambiguous_assignment/possibly_filed_late flags, representative filings don't replace individual duties, and not_filed candidates are not confirmed and are enumerated in scope_caveats. This gives the agent a realistic model of the tool's behavior and limitations.

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 description front-loads the core purpose and main caveat in the first two sentences, then uses bullet points to enumerate behavioral rules without repetition. It is long but each bullet adds a distinct fact relevant to invocation or interpretation, making it appropriately sized for a tool with 6 parameters and nuanced judgment logic.

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?

There is no output schema, but the description names result categories (on_time, late_candidates, not_filed_candidates), explains due:false and non_filing_is_signal semantics, and points to scope_caveats for excluded cases. It also covers authentication, limits, representative-filing exceptions, and snapshot timing, giving the agent enough information to call and interpret the tool correctly.

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%, with each parameter (year, group, today, duties, companies, year_month) already documented. The description adds some operational context such as the 80-company limit and the May snapshot default, but it does not meaningfully enhance the semantics of individual parameters beyond what the schema provides. Baseline 3 is appropriate.

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 opens with '정기공시 이행 점검' and specifies that it checks periodic disclosures of J004 and J009 per company, whether filed and on time. It also explicitly states '내용의 정확성은 보지 않습니다' (does not check content accuracy), which distinguishes it from content-review-focused sibling tools. This is a specific verb+resource with clear sibling differentiation.

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?

The description provides clear context: deadlines are calendar-fixed and judged by receipt date, J009 non-filing is not a signal (non_filing_is_signal:false), due:false items are not judged as non-filing, and representative company submission does not substitute individual duty. It also gives operational constraints like EGROUP_API_KEY requirement and the 80-company limit. However, it does not explicitly name alternative tools or state when to use a sibling instead, so it lacks explicit when-not-to-use routing.

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