MCP server for curating zero-plastic refillable home bundles with sustainable alternatives to single-use plastic bottles
This server has a single tool 'execute_skill_action' with critical definition gaps. The tool description is extremely vague (58 chars, below the 10-1024 baseline). No input schema is visible in the source code, the tool appears to be declared only in a JSON status message with no formal registration, parameter definitions, or output schema. The implementation is a stub that prints a status message and exits; there is no actual tool logic. Per HARD SCORING RULES, missing input schema → schema score 0; vague description under 20 chars → description score capped at 20. Tool definition is inferred from JSON output, not explicitly registered → overall capped at 50. Average of single tool: 12.
Execute skill action for zero plastic refill sustainable home DTC
No input schema visible. Tool 'execute_skill_action' has no formal parameter definitions, types, or constraints.
Tool description is vague and too short (58 chars). 'Execute skill action for zero plastic refill sustainable home DTC' does not explain WHAT the tool does, WHEN to use it, or WHAT it returns. LLMs cannot determine when to select this tool.
Tool definition is inferred from JSON status output, not explicitly registered via MCP protocol. No formal tool registration with name, description, and schema visible in code.
No output schema documented. Clients cannot know what fields to expect from 'execute_skill_action'. The client.py shows a curate_zero_plastic_home_bundle() method returning a dict, but this is not connected to the MCP tool definition.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 17 | 2026-07-28+ | v2 |
No error handling or recovery guidance. Tool has no documented error cases, retryability, or actionable error messages. LLMs cannot self-correct on failure.