Loading ToolBench
MCP server for detecting and automatically rebalancing database partition hotspots to optimize query performance and prevent bottlenecks
Critical failures across all dimensions. The single tool 'execute_skill_action' has a minimal description (58 chars, below the 10-1024 baseline), a single parameter with a default but no type validation, and no documented output schema. The mcp_server.py implementation is a stub that prints JSON and exits, it does not actually implement the MCP protocol (no request/response handling, no tool invocation dispatch). Tool definitions are inferred from client.py, not explicitly registered in the server. No error handling, no parameter validation, no security considerations.
Execute database partition hotspot detection and rebalancing action
Tool definition inferred from client.py, not explicitly registered in MCP server.
No output schema documented. LLM cannot predict response structure (table_name, total_shards_evaluated, hotspot_mitigation_plan, etc.). Violates pattern:tool requirement.
Parameter 'table_name' has no type declaration in schema (only a default value).
Description is 58 characters ('Execute database partition hotspot detection and rebalancing action'). Lacks WHAT, WHEN, and prerequisites. Does not explain when to use vs. similar tools or what the return value contains.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 22 | 2026-07-28+ | v2 |
No error handling, recovery guidance, or actionable error messages. If the tool fails, LLM has no guidance on retry, user input, or next steps.