Standalone MCP server + GUI for Couchbase Enterprise Analytics and Capella Analytics
Server has 4 tools with basic schemas and descriptions, but significant gaps prevent higher scoring. All tools have descriptions (10-60 chars, below the 50-200 char baseline for LLM optimization) and input schemas with type info. However, descriptions lack actionable context (WHEN to use, prerequisites, dependencies). Parameter descriptions are minimal. No output schemas documented. Error handling and recovery guidance absent. Tools follow verb_noun naming but descriptions don't explain distinctions between similar tools (get_service_config vs get_analytics_settings). No tool annotations (readOnlyHint/destructiveHint) despite clear READ/WRITE risk levels. Composition is reasonable (4 focused tools), but parameter design could accept human-friendly identifiers (cluster name defaults, validation guidance missing).
Return cluster-wide Analytics settings (e.g. replica count).
Return the Analytics service-level configuration.
Update cluster-wide Analytics settings (e.g. numReplicas).
Update Analytics service-level configuration (e.g. resultTtl, compilerParallelism).
Descriptions too brief and lack actionable context. 'Return the Analytics service-level configuration' (54 chars) does not explain WHEN to call this vs get_analytics_settings, what fields are returned, or prerequisites. Baseline for LLM optimization is 50-200 chars with WHAT/WHEN/WHY.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields (e.g., does get_service_config return resultTtl, compilerParallelism, or other fields?). Agents must guess structure.
No tool annotations despite clear risk levels. update_service_config and update_analytics_settings are marked WRITE but lack destructiveHint annotation. get_* tools lack readOnlyHint. Agents cannot distinguish safe from risky operations.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | <=2025-11-25 | v2 |
Parameter descriptions missing or minimal. 'settings' in update_service_config has description 'Configuration settings to update' but does not specify valid keys, format, constraints, or examples. 'num_replicas' lacks range (min/max) guidance.
No error handling or recovery guidance. Tools do not document what errors are possible, whether they are retryable, or what the LLM should do next. A failed update returns nothing actionable.