A local MCP server that multiplexes tools from native providers and remote MCP servers, with policy-based access control and audit logging
Single tool 'toolmux.remote-auth-refresh' has a well-structured input schema with proper types and descriptions, but the tool description is minimal (67 chars, below the 194-char baseline). Parameter descriptions are present and clear (e.g., 'Name of a single toolbox to refresh'), meeting the pattern:tool-description requirement. However, the tool description itself lacks context on WHEN to use it, WHAT it returns, or error recovery guidance. No output schema is documented. The tool performs a WRITE operation (credential refresh) but the description does not explicitly state this is a state-modifying action, violating pattern:command-tool. No error handling guidance is provided.
Refresh stored authentication credentials for remote MCP servers
Tool description is too brief (67 chars vs 194-char baseline). Lacks WHEN to use, WHAT it returns, and error recovery guidance. LLMs cannot determine selection criteria.
No output schema documented. LLMs cannot plan downstream calls or extract return values. Violates pattern:tool requirement for structured output.
Tool performs WRITE operation (credential refresh) but description does not explicitly state this is state-modifying. Agents need to know which calls are safe to retry.
No error handling guidance. If credential refresh fails, LLM has no recovery path. Missing pattern:recovery-guide implementation.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2025-06-18+ | v2 |
Parameter 'probe' has a default (true) but no explanation of what probing does or why it defaults to true. Undocumented defaults invite misuse.