Scan Korean contracts and terms clause by clause to flag renewal, termination, penalty, repair, and liability signals with cited statutes, figures, conflicts, and grades—not legal verdicts.
계약서·약관 전문(200자 이상)을 조항별로 훑어 기간·갱신·증액·대항력·해지·위약금·수선·권리금·면책·중개·신고의 검토 신호를 근거 조문(법령·조문·시행일)과 수치·충돌·등급으로 돌려준다(위법 판정 아님).
| Name | Required | Description | Default |
|---|---|---|---|
| asOf | No | 기준일(YYYY-MM-DD, 기본 오늘) | |
| text | Yes | ||
| docType | No | ||
| maxFindings | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes this is a safe read, so the bar is lower, and the description adds real context beyond it: it discloses the shape of the return (근거 조문 with 법령·조문·시행일, plus 수치·충돌·등급) and an explicit non-goal (not a legal determination). It does not cover latency, limits, or failure behavior, which keeps it from a 5.
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?
It is a single front-loaded sentence that leads with the action and input, then the output, then the disclaimer, with no filler. The eleven-item signal enumeration makes it dense, but each item is load-bearing content rather than padding.
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?
With no output schema, the description must carry return-value meaning and it does describe the finding categories and evidence fields, which is adequate. It is thin on the remaining gaps an agent needs: what the 등급 scale means, how docType changes behavior, what maxFindings does, and how the 100k-character input limit interacts with the 200-character floor.
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 only 25% (only asOf is documented), so the description must compensate and does so only partially: it supplies the 200-character minimum for text, which the schema lacks, and its signal list loosely maps to docType. The docType enum values, maxFindings, and the overall text limit are never explained, leaving half the parameters undocumented in both places.
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 gives a specific verb (훑어/scan clause-by-clause) and a specific resource (계약서·약관 전문), and enumerates the exact signal categories it returns, so its function is unambiguous. It does not explicitly name or contrast with the sibling legal-research tools (statute_find, article_get, citation_audit), but the task is distinct enough that an agent can separate it without opening schemas.
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 is implied through the input constraint (full text of 200+ characters) and the scope exclusion '위법 판정 아님' (this is not a legal-violation verdict), which usefully tells the agent when the output should not be relied on. However, no alternative tool is named and no positive condition for choosing this over statute_find/precedent_trace is stated, so guidance stays implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.