Skip to main content
Glama

Liuwangcun Chinese Compliance Tools

装修合同风险点检测

decoration-contract

装修合同风险点检测:签装修合同前过一遍:增项无上限、付款节点、材料品牌、工期违约金、质保、验收标准、单方变更、口头承诺。 检测维度:增项无上限、付款节点不利、材料品牌不明、工期无违约金、质保缺失、验收标准模糊、单方变更、口头承诺不落纸。传入整段中文原文,返回命中风险点、等级与整改建议。适用场景:Agent 处理合同/文案/协议/政策文本时,在交付给人之前做一道确定性合规体检。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "decoration-contract"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes待检测的中文原文(合同条款、广告文案、协议、政策文本等整段贴入)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full disclosure burden, and it does state the return shape (hit risk points, severity level, remediation suggestions) and that the check is deterministic rather than generative. It omits edge-case behavior, such as what happens with non-contract text or very long inputs, and gives no length or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is correctly front-loaded, but the eight detection dimensions are listed twice in near-identical form (once in the pre-signing check list, once after 检测维度), which is pure repetition in an otherwise short description. Trimming the duplicate list would make it markedly tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-text-in tool with no output schema, the description covers what an agent needs: the input form, the categories examined, and the shape of the result (risk points, level, suggestions). Only failure and boundary behavior are left unstated, which is a minor gap at this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter with 100% schema coverage, so the baseline is 3. The description reinforces that the whole original text should be pasted in as one block (传入整段中文原文), matching the schema's own wording, but adds no new format, length, or encoding guidance beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and domain (装修合同风险点检测 / risk-point detection on renovation contracts) and enumerates the eight risk categories it checks (增项无上限, 付款节点, 材料品牌, 工期违约金, 质保, 验收标准, 单方变更, 口头承诺). This makes it unambiguously distinct from the template siblings (decoration-template, rental-template) and from zhuangxiu-budget, which computes budgets rather than auditing contract text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear when-to-use context: before signing a renovation contract, and as a deterministic compliance check an Agent runs before delivering text to a human. It does not, however, name any alternative or exclusion, such as routing to decoration-template when the user needs a draft rather than an audit, so the agent must infer the boundary from the sibling names alone.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.