Four tools with basic verb-noun naming (get_*, search patterns). All have descriptions (10-50 chars, below 194-char baseline). Input schemas present but minimal: single string parameters with descriptions. No output schemas documented. No error handling guidance, no pagination support, no structured response documentation. Parameters lack type diversity and constraints. No tool annotations (readOnlyHint, etc.). Composition is reasonable (each tool has one responsibility), but descriptions are too terse to guide LLM selection effectively.

• Expand each tool description to 100-200 characters. Include: what the tool does, when to use it vs. similar tools, and what structure is returned. E.g., 'Search for clusters by name or configuration. Returns a list of matching cluster IDs and names. Use this to discover available clusters before calling get_cluster_details.'
• Document output schemas for all tools. Specify that search tools return {results: [{id, name, ...}], total_count} and detail tools return {id, name, config, ...}. This enables LLMs to extract IDs for chaining calls.
• Add error handling guidance to descriptions. E.g., 'If no clusters match, try a broader query or check the cluster name spelling. Returns empty list if no matches found.'
• Implement pagination for search tools: add optional limit (default 20, max 100) and offset parameters. Return total_count so LLMs know if more results exist.
• Add tool annotations via FastMCP: mark all four tools with readOnlyHint=true to signal they are safe to call without user confirmation.

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

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