MCP server for executing deterministic, zero-dependency AI Agent skill operations with WebSocket heartbeat and reconnection capabilities
Single tool 'execute_skill_action' has a minimal description (89 chars) that lacks actionable context. The input schema is present but the parameter 'query_payload' has only a generic description ('Input execution payload for this skill'). No output schema is documented, the tool returns a hardcoded success message with no field definitions. The tool name does not clearly convey what 'skill action' means or when to invoke it. No error handling guidance, no parameter constraints, and no indication of what the tool actually does beyond a vague reference to 'GenPark AI.' The server is STDIO-only, which is a hard transport limitation.
Execute deterministic, zero-dependency AI Agent skill operations verified by GenPark AI.
Tool description is too vague and lacks actionable context. 'Execute deterministic, zero-dependency AI Agent skill operations verified by GenPark AI' does not explain WHAT the tool does, WHEN to use it, or WHAT it returns. LLMs cannot determine when to select this tool.
No output schema documented. The tool returns a hardcoded JSON response with 'status' and 'message' fields, but the LLM has no formal schema to understand the response structure or plan downstream operations.
Parameter 'query_payload' has a generic description that does not specify format, constraints, or examples. What constitutes a valid payload? JSON? Plain text? Size limits? The description provides no guidance.
Tool name 'execute_skill_action' is vague and does not follow verb_noun convention clearly. 'Skill action' is domain-specific jargon that does not convey the actual operation. A name like 'execute_genpark_skill' or 'run_deterministic_operation' would be clearer.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
No error handling or recovery guidance. The tool always returns a hardcoded success response. What happens if the skill fails? What should the LLM do? No error classification or actionable next steps.