Server exposes 6 cricket schedule tools via Spring AI MCP framework. All tools have basic descriptions (15-40 chars) and input schemas with type definitions. However, descriptions are minimal and lack LLM-optimized guidance on WHEN to use each tool vs. alternatives. Parameter descriptions are present but generic. No output schemas documented. No error handling guidance visible. Tools follow verb_noun naming (getAllMatches, getMatchesByTeam) but descriptions do not explain selection criteria or dependencies between tools.

• Expand tool descriptions to 50-150 chars. Example: 'getMatchesByTeam: Retrieve all IPL 2025 matches where the specified team plays (home or away). Use this when filtering by a specific team; use getMatchesByDate for date-based filtering.' This clarifies selection criteria and guides LLM tool choice.
• Document output schemas for all tools. Specify that responses include fields like matchId, team1, team2, date, venue, status. This enables agents to chain tools and extract required data without guessing.
• Add enum constraints for teamName parameter. List valid IPL 2025 teams (e.g., 'CSK', 'MI', 'RCB', 'KKR', etc.) so LLMs pick from known options instead of hallucinating team names.
• Add error handling guidance. Document what happens on invalid input: 'If teamName is not found, returns empty list. Valid teams: [list]. If date format is invalid, returns 400 error with format hint: yyyy-MM-dd.'
• Implement and document pagination for getAllMatches. Add optional limit (default 20, max 100) and offset parameters. Return total count so agents know if more results exist. Cap results at 50 by default to prevent context bloat.