Server has 7 tools with basic descriptions and input schemas, but significant gaps in parameter documentation, output schema clarity, and error handling guidance. All tools are READ_ONLY (good for safety), but descriptions lack LLM-optimized structure. Parameter descriptions exist but are minimal (avg ~40 chars, below 72-char baseline). No output schemas documented. Error handling returns generic error dicts without recovery guidance. Tool names follow verb_noun pattern (positive), but descriptions don't explain WHEN to use each tool or dependencies between them.

• Document output schemas for all tools. E.g., 'Returns: {"total_messages": int, "unique_senders": int, "avg_message_length": float, "longest_message": int, "top_senders": {str: int}}' so LLMs know what fields to expect.
• Enhance error messages with recovery guidance. Instead of {'error': 'Failed to fetch messages'}, return {'error': 'Failed to fetch messages. Ensure Full Disk Access is enabled in System Preferences > Security & Privacy. If enabled, try restarting the MCP server.'}
• Expand parameter descriptions to 50-200 chars with constraints. E.g., 'top_n: Number of top words to return (default: 10, range: 1-100). Higher values reveal less common vocabulary; lower values focus on core terms.'
• Add pagination to list_contacts and search_messages. Accept offset/limit params, return total_count and next_cursor. Cap default limit at 20, max at 100 to prevent context window exhaustion.
• Add tool selection guidance in descriptions. E.g., get_conversation: 'Use this after search_messages to retrieve full context with a contact. Requires contact name/phone/email.' This helps LLMs chain tools correctly.