MCP server that exposes FuncDock serverless functions as tools, allowing invocation of deployed Node.js functions via HTTP methods
Single tool with severely deficient naming, description, and schema. Tool name '{functionName}__{routePath}__{method}' is a template placeholder, not a verb-noun action name, violates core naming pattern. Description is generic boilerplate ('Invoke {method} {routePath}...') with no context for LLM selection. Input schema present but parameters lack descriptions (functionName, routePath, method, body, query, params all undescribed). No output schema documented. No error handling guidance. Tool appears dynamically generated from function metadata rather than explicitly registered with production-grade definitions.
Invoke {method} {routePath} on function {functionName}
Tool name is a template placeholder, not a verb-noun action. '{functionName}__{routePath}__{method}' does not start with an action verb and is not human-readable. LLMs cannot infer intent from this name.
Description is generic boilerplate with no context. 'Invoke {method} {routePath} on function {functionName}' does not explain WHEN to use this tool, what it returns, or how it differs from similar tools. LLMs cannot select it confidently.
All input parameters lack descriptions. 'functionName', 'routePath', 'method', 'body', 'query', 'params' have no guidance on format, constraints, or expected values. LLMs cannot infer parameter semantics from names alone.
No output schema documented. Tool response structure is unknown to the LLM. Cannot plan downstream tool calls or extract required fields.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 29 | 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 LLM recovery.