ClawQL Model Context Protocol server providing tools for audit, cache, memory, sandbox execution, and provider integrations
ClawQL MCP exposes only 2 tools ('cache' and 'audit') with minimal documentation. Both tools lack visible input schemas, parameter definitions, and detailed descriptions. Tool descriptions are generic placeholders ('ClawQL Core cache tool', 'ClawQL Core audit tool') under 30 characters, far below the 194-char baseline for production tools. No evidence of parameter documentation, output schemas, or error handling guidance. Source code provided (Makefile, mcp.json) shows deployment configuration but no tool implementation details. Tool definitions appear inferred rather than explicitly registered with schemas.
ClawQL Core audit tool
ClawQL Core cache tool
No input schemas visible for either tool. Cannot verify parameter types, constraints, or required fields.
Tool descriptions are generic placeholders (5-20 chars) far below 194-char baseline. Descriptions do not explain WHAT the tool does, WHEN to use it, or what it returns.
No parameter documentation visible. Cannot determine what inputs each tool accepts, their types, constraints, or defaults.
No output schema documentation. LLMs cannot plan downstream calls or extract required fields from results.
Inferred effective spec: 2026-07-28+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
Tool names 'cache' and 'audit' lack action verbs. Should be 'get_cache', 'clear_cache', 'view_audit_log', etc. Current names do not convey what action occurs when called.