OpenClaw + Trae CN MCP Server integration providing AI quantitative trading tools and project management capabilities
Server provides 6 tools with complete input schemas and basic descriptions, but falls short of production quality. All tools have descriptions (10-30 chars, below the 50-200 char baseline for LLM optimization) and JSON Schema with types. However, descriptions lack actionable context, they state WHAT but not WHEN or WHY. Parameter descriptions are minimal (e.g., 'stock code' vs 'stock code (2-6 uppercase letters, e.g., 600519)'). No output schemas documented. No error handling guidance. No tool annotations (readOnlyHint/destructiveHint). create_project is marked WRITE but has no confirmation/dry-run pattern. Tools lack composition guidance (e.g., which tools chain together). Naming is acceptable (verb_noun style) but generic (stock_quote, risk_analysis). No pagination, no batch variants, no recovery hints.
创建 AI 量化交易项目
风险管理分析
运行量化策略回测
AI智能选股
获取股票实时行情
计算技术指标
Descriptions are too short (10-30 chars) and lack actionable context. LLMs cannot determine WHEN to use each tool or what it returns. Baseline is 50-200 chars with WHAT/WHEN/WHY guidance.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields. Every tool must declare its return structure.
create_project is a WRITE tool with no confirmation/dry-run pattern. Agents can accidentally create projects without verification. Irreversible operations need confirmation_request pattern.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 54 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Clients cannot determine which tools are safe to retry or have side effects.
Parameter descriptions are minimal or missing context. E.g., 'stock code' does not explain format, valid range, or examples. Descriptions should state constraints inline.