정정공시 리스크 진단

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

With no annotations, the description carries the full burden and does well: it explains what the tool returns (violation status, exemption paths, recommendations with cited provisions), how it uses originalDeadline to calculate golden time and mitigation schedules, and that exemptions are discretionary judgment material. It also notes local rule behavior without needing an API key.

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 well-structured with an intro paragraph and four bullet points, each covering a distinct behavioral aspect. Every sentence adds substance, with no redundancy.

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 no output schema and no annotations, the description adequately explains return values and behavior: it lists the output types (violation status, exemption paths, recommendations, schedules) and the special path for transaction_changed. It also notes the discretionary nature of exemptions, making it complete for a diagnostic tool.

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 covers 100% of parameters with descriptions. The description adds value by explaining how errorType maps to violation/exemption logic and how originalDeadline triggers additional calculations, plus the special transaction_changed case. It also references crossConfirmable and newlyDesignatedWithin30d via exemption path names.

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 diagnoses correction disclosure risk based on the penalty notice, explaining it evaluates whether the original disclosure constitutes a violation and returns exemption paths and recommendations. This distinguishes it from siblings like find_precedents or check_disclosure_duty by focusing specifically on correction risk.

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 implies when to use the tool (to assess whether a correction incurs a penalty) and provides specific guidance for transaction_changed, stating it is not a correction but a new disclosure obligation. However, it does not explicitly compare to sibling tools or state when not to use it.

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