대규모내부거래 기한 감사

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

No annotations are provided, so the description carries the full burden. It is exceptionally transparent: it discloses the output payload (delay days, penalty, golden-time status, basis), the 'candidate not confirmed' caveat, exclusion of correction filings, separate classification of special financial-transaction forms, range_too_large handling, permanent cache behavior, and auth requirements. This goes far beyond what an agent could infer from the schema.

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 is compact and well-structured: a single lead sentence defines the core function, followed by five focused bullet points that each add a distinct, non-redundant caveat. Every sentence earns its place with no filler or repetition.

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?

Given the complexity of a date-range audit tool with six optional/required parameters and no output schema, the description is remarkably complete. It covers input selection logic, the audit method, expected output fields, special-form handling, corrections exclusion, range-limit feedback, caching, and auth requirements, giving the agent a full mental model.

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?

The schema already describes all parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantics by explaining that group and companies are mutually exclusive selectors with one required—a constraint not reflected in the schema's required array. It also links today to the golden-time calculation and clarifies that from/to are receipt-date based, adding value over the schema 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?

The description opens with a specific verb (감사해) and resource (대규모내부거래(J001) 공시), clearly stating it audits disclosures to find deadline-delay candidates. It distinguishes the tool from siblings by describing the exact comparison method (receipt date vs. board resolution date) and the listed/unlisted business-day thresholds.

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 makes the intended context clear: audit J001 disclosures for a business group or company list over a date range. It also flags prerequisites such as EGROUP_API_KEY and warns that unjoined coverage companies are omitted. However, it does not explicitly name alternative tools or state when not to use it, stopping short of full 'when vs. alternatives' guidance.

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