기업집단현황공시(J004) 정합성 자가점검

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It thoroughly explains that only document-internal consistency is checked, not underlying accounting truthfulness, and warns that include_generic_totals may produce false positives due to merged-cell tables. It also describes the unit-error hint behavior, demonstrating transparency about how the tool operates.

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 efficiently structured: an opening sentence states the main purpose and importance (84% of violations are J004), followed by a clear bullet list of capabilities, a limitation caveat, and cross-references to other tools. Every sentence adds value with no filler.

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 tool with four parameters and no output schema, the description comprehensively covers purpose, usage scenarios, limitations (internal consistency, false positives), parameter behavior, and integration with assess_correction_risk. It provides sufficient context for an agent to decide when and how to invoke the tool, including how to interpret results indirectly through the max_issues parameter.

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% with detailed descriptions for all parameters (e.g., compare_rcept_nos explains unit matching, include_generic_totals explains experimental nature and risks). The description reinforces these points but does not add substantial new meaning beyond the schema, so the baseline of 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 clearly states the tool's purpose: it recalculates all mechanically re-calculable items in J004 corporate group status disclosures to find inconsistencies. It specifies the scope (financial status checks, unit error hints) and distinguishes itself from other tools by noting it only checks internal consistency and recommending assess_correction_risk for correction decisions.

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 explicitly states when to use it: for pre-submission self-check or post-submission inspection. It also provides guidance on alternatives, noting that it does not judge truthfulness and should be used with assess_correction_risk for correction. The bullet points explain trade-offs for parameters like include_generic_totals and compare_rcept_nos, giving clear usage context.

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