MCP server providing tools for calculations, user management, file system access, and code-related prompts via HTTP StreamableHTTP transport
Server has 6 tools with minimal quality. All tools lack proper descriptions (Chinese text only, under 20 chars in English context). Input schemas present but sparse, most parameters lack type constraints or detailed descriptions. No output schemas documented. Tool names lack action verbs (health, calculate_sum, calculate_average, calculate_stats, get_user_info, validate_user). No error handling guidance, no parameter validation rules, no recovery paths. Naming inconsistency: 'calculate_*' vs 'get_*' vs 'validate_*' without clear semantic distinction. No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Critical: descriptions are in Chinese and too brief to guide LLM selection.
计算数字列表的平均值
计算数字列表的基本统计信息
计算数字列表的总和
获取用户信息
健康检查工具
验证用户ID是否有效
All tool descriptions are in Chinese and under 20 characters. LLMs cannot determine when/why to select tools without clear English descriptions explaining WHAT the tool does, WHEN to use it, and WHAT it returns.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required data without knowing what fields to expect in responses.
Tool 'health' lacks action verb. Generic names like 'health' do not convey intent. Should be 'check_health' or 'get_health_status' to match verb_noun convention.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 29 | <=2025-11-25 | v2 |
Parameter 'numbers' in calculate_* tools lacks type constraint (array of what?). Description does not specify format, range, or element type. Should state: 'Array of numbers (integers or floats). Minimum 1 element, maximum 1000 elements.'
No error handling guidance. Tools do not document what happens on invalid input (empty array, non-numeric values, null). LLMs cannot self-correct without actionable error messages.