The server defines 2 tools with Islamic finance domain-specific calculations (Musharakah and Mudharabah profit/loss distribution). Both tools have clear descriptions and explicit input schemas with proper JSON Schema definitions. However, there are notable gaps: (1) no documented output schemas are visible in the source code, (2) parameter descriptions are present but minimal (10-50 chars), below the 72-char baseline, (3) no error handling or recovery guidance is visible, (4) no tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite both being read-only operations. The naming is domain-specific and clear (calculate_musharakah, calculate_mudharabah) but lacks the verb_noun pattern typical of 90% of A+ tools. Input parameters have types and constraints (minimum/maximum on numeric fields, minItems on arrays) which is a positive signal, but descriptions lack actionable guidance (e.g., what happens if profit ratios don't sum to 1, what tolerance is acceptable).

• Add explicit output schema documentation for both tools. Document the structure of profit/loss distributions returned (e.g., 'returns: {partner_name: string, share: number, amount: number}').
• Expand parameter descriptions to 50-150 characters. For 'profitRatio', add: 'Array of profit-sharing percentages (0 - 1) that MUST sum to exactly 1.0. If omitted, defaults to capital-proportional distribution per Shariah.'
• Add tool annotation 'readOnlyHint: true' to both tools since they perform no mutations.
• Document what happens when constraints are violated. E.g., for 'profitRatio', add error handling: 'Error if ratios don't sum to 1.0, LLM will receive "Invalid ratio sum: X, expected 1.0. Adjust and retry."'
• Add dependency hints in descriptions. E.g., 'For Musharakah, always ensure you have at least 2 partners; for Mudharabah, capital provider and entrepreneur ratios must sum to ≤1.0 (remainder is retained by provider).'
• Document numeric precision and currency assumptions (e.g., 'All amounts in base currency with 2 decimal places').
• Provide example invocations in tool descriptions to guide LLM usage (but not as example values, document as a separate examples section if supported).