Single tool with basic structure but significant gaps. Tool name 'calculate_bmi' is action-verb compliant and clear. Description is present (47 chars) but minimal, lacks context on when to use, prerequisites, or return value semantics. Input parameters have types (float) and descriptions, meeting baseline requirements. No output schema documented. No error handling guidance beyond ValueError for height ≤ 0. No pagination, composition, or idempotency considerations (not applicable for this simple tool). Lacks security annotations and audit trail patterns. Meets minimum viability but falls short of production-grade quality.

• Expand tool description to 80 - 150 chars: 'Calculate Body Mass Index (BMI) from weight and height. Returns BMI as a float (kg/m²). Use this to assess health metrics or validate user input. Requires height > 0 and weight > 0.'
• Document output schema explicitly: 'Returns: float (BMI value in kg/m², typically 15 - 40 for adults).'
• Add parameter constraints to descriptions: 'weight_kg: Weight in kilograms (0.5 - 500 kg, typically 40 - 150 for adults).' and 'height_m: Height in meters (0.5 - 2.5 m, must be > 0).'
• Enhance error handling: catch ValueError and return structured error with recovery hint: {'error': 'Invalid input', 'message': 'Height must be greater than zero.', 'suggestion': 'Verify height is a positive number in meters.'}
• Add tool annotations in FastMCP decorator: @mcp.tool(annotations={'readOnlyHint': True, 'idempotentHint': True}) to signal safety properties to agents.