An MCP server that answers questions about Azure Services using a knowledge base backed by Neo4j and OpenAI
Single tool 'AzureKnowledgeBaseK' has critical definition gaps. Tool name violates verb_noun convention (ends with 'K', unclear intent). Description is minimal (34 chars, below 50-char baseline for clarity). Input schema present but parameter 'question' lacks description entirely, violates pattern:tool-description. No output schema documented. No error handling guidance. No pagination, no structured response format specified. Tool appears to return raw string, not structured object. Missing all composition and chaining metadata.
Answers questions about Azure Services
Tool name 'AzureKnowledgeBaseK' violates verb_noun convention and is ambiguous. The trailing 'K' is unexplained; LLMs cannot infer action from the name alone.
Parameter 'question' has no description. LLMs cannot determine expected format, constraints, or examples. Violates pattern:tool-description requirement that every parameter must have a non-empty description.
No output schema documented. Tool returns raw string (answer.Result), but LLMs need to know: is this markdown, plain text, structured JSON? What fields should they extract? Violates pattern:tool requirement for documented return types.
No error handling or recovery guidance. If KnowledgeService.GetAnswerAsync() fails (Neo4j down, OpenAI API error, invalid question), the tool returns nothing actionable. LLMs cannot self-correct or retry intelligently.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 28 | <=2025-11-25 | v2 |
Tool description 'Answers questions about Azure Services' is generic (34 chars). Does not explain WHEN to use it vs other tools, what knowledge base it queries, or what format answers take. Below 50-char baseline for clarity.