A federation gateway skill that resolves MCP tools across multiple connected gateways (postgres-mcp, github-mcp, s3-storage-mcp) and returns federated tool schemas with routing latency and cache metrics
This server has a single tool 'execute_skill_action' with critical definition gaps. The tool description is present but extremely vague (47 chars, below the 50-char minimum for actionable guidance). No input schema is visible in the source code, the mcp_server.py only prints a JSON status message with a tool list, not actual tool definitions with parameters. The client.py demonstrates schema resolution for OTHER gateways (postgres-mcp, github-mcp) but does not define the schema for execute_skill_action itself. Without visible input/output schemas, parameter descriptions, or error handling, this tool cannot be reliably invoked by an LLM. The tool name 'execute_skill_action' is also generic and does not follow verb_noun conventions (e.g., 'invoke_skill', 'run_skill_action').
Execute a skill action through the MCP federation gateway
No input schema visible for execute_skill_action. Tool definition in mcp_server.py only prints a status message; no actual tool registration with parameters, types, or constraints.
Tool description is 47 characters ('Execute a skill action through the MCP federation gateway'), below the 50-char minimum for actionable LLM guidance. Does not explain WHEN to use it, WHAT it returns, or HOW to invoke it.
No parameter descriptions or types defined. LLMs cannot infer what parameters execute_skill_action accepts, their types, constraints, or whether they are required.
No output schema documented. LLMs cannot plan downstream tool calls or extract relevant data from the response.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 19 | 2026-07-28+ | v2 |
No error handling or recovery guidance. Tool provides no actionable error messages, categorization (retryable vs fatal), or next-step hints for LLMs.