Loading ToolBench
Official Model Context Protocol (MCP) Server for QiuXiaoCe (球小策) Football Big Data & AI Analysis.
Server has 4 tools with basic schemas and descriptions in Chinese. All tools are READ_ONLY and follow verb_noun naming (get_*, search_*). However, descriptions lack depth on WHEN to use each tool vs alternatives, parameter descriptions are minimal, and output schemas are completely undocumented. No error handling guidance, no pagination support despite potential for large result sets, and no tool annotations. Schemas are present but sparse, most parameters lack detailed constraints or format guidance.
获取欧洲五大联赛实时积分榜数据（免费开放）。包含排名、球队中英文名、场次、胜平负、积分等。
获取今日重点足球赛事列表与彩票场次对应快讯。
足球联赛与赛事检索（免费开放）。返回联赛 ID、中英文名称与国家。
中英文足球俱乐部与赛事智能检索（免费开放）。返回球队官方规范 ID、中文译名、英文全称及国家。
No output schemas documented. LLMs cannot predict response structure, forcing them to guess field names for downstream tool calls or data extraction. All 4 tools return JSON.stringify(res) with no schema definition.
Parameter descriptions are minimal or missing context. 'league_id' example lists IDs but no explanation of what league_id=39 means in context. 'query' param lacks format guidance (min/max length, character restrictions). No dependency hints (e.g., 'search_leagues first if you don't know the league_id').
No pagination or result limits documented. search_teams and search_leagues could return hundreds of results, blowing context window. No limit parameter, no offset/page support, no total_count in response schema.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | 2026-07-28+ | v2 |
No error handling guidance. handleToolCall catches errors and returns generic -32603 with only err.message. No recovery hints (e.g., 'League not found. Try search_leagues() first'). No categorization of retryable vs fatal errors.
Tool descriptions lack WHEN/WHY guidance. 'get_standings' says what it returns but not when to call it vs search_teams. No hints on prerequisites or common workflows. Descriptions are 60-80 chars; baseline for A+ is 50-200 chars with clear intent.