Two tools with minimal definitions. Both have short descriptions (34-40 chars, below the 50-200 char baseline for LLM-optimized descriptions). Input schemas are present but extremely sparse, only 'id' parameter with basic string type, no constraints, enums, or validation guidance. No output schemas documented. No error handling guidance. Tools are read-only but lack explicit idempotentHint annotations. Naming is acceptable (get_instances, get_tenants) but descriptions fail to explain WHEN to use each tool or what distinguishes them.

• Expand descriptions to 80-150 chars. Example: 'Retrieve instance details from Neo4j Aura API. Use this to check instance status, connection info, and configuration. Requires a valid instance ID (UUID format).'
• Add parameter description for 'id': 'The Neo4j Aura instance identifier (UUID format, e.g. 550e8400-e29b-41d4-a716-446655440000). Obtain from list_instances or the Aura console.'
• Document output schema for each tool. Example: 'Returns {id: string, name: string, status: string, created_at: ISO8601, region: string, ...}'. Include which fields are safe to pass to downstream tools.
• Add error handling guidance: 'If instance not found, try list_instances() to discover valid IDs. If auth fails, verify CLIENT_ID and CLIENT_SECRET environment variables.'
• Add tool annotations: set readOnlyHint=true and idempotentHint=true in the schema to signal safe retry behavior to agents.

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry