정정공시 리스크 진단

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

With no annotations provided, the description carries the full disclosure burden and excels at it. It reveals the core insight (correction itself is not a violation, only the original state matters), discloses that it computes golden time and reduction schedules from originalDeadline, and — critically — states that exemptions/reductions are FTC discretion, returning 'judgment materials, not confirmations'. This honesty about output nature is exemplary and prevents agent overconfidence.

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 front-loaded with the single most important insight (correction isn't a violation; the problem is the original state) before the bullet list. Each bullet earns its place — errorType behavior, deadline calculations, the transaction_changed exception, and the discretion caveat. It is dense but efficiently organized with zero filler; only the missing output-format note prevents a 5.

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 legal-risk tool with 6 parameters, 2 enums, and no output schema or annotations, the description is commendably complete. It explains what comes back (violation status, exemption paths, recommendations with cited clauses), the schedule calculations, and the discretionary nature of outcomes. It doesn't describe the exact output structure (field names, format), but for a judgment-tool it conveys everything an agent needs to invoke and interpret it 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 coverage is 100%, with detailed descriptions for all 6 parameters including full enum semantics for errorType and regime. The description adds modest value beyond the schema — it links originalDeadline to the golden-time and 75→50→30→20% reduction schedule, and explains transaction_changed is a new duty rather than a correction. These are useful additions, but the schema already documents parameter meaning thoroughly, so the description's marginal contribution is limited.

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: diagnosing the folk belief that correcting a disclosure triggers fines, using the penalty notice original text. It specifically states the tool assesses whether the original disclosure state (omission, false, delay) constitutes a violation per errorType, which is a specific verb+resource+scope. It doesn't explicitly name sibling alternatives, but the function is unambiguous and none of the 17 siblings perform correction-risk assessment.

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?

Usage context is implied rather than stated. The description explains behaviors (errorType-based violation status, originalDeadline golden-time calculation) but never explicitly says 'use this when' or names when NOT to use it relative to siblings like check_disclosure_duty or detect_undisclosed_transactions. The transaction_changed bullet hints that such cases route to a re-disclosure path, but no alternative tool is named.

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