36 tools with consistent verb-noun naming and Zod schemas. Descriptions present but brief (avg ~60 chars, below 194-char baseline). All parameters have type definitions and descriptions. Output schemas are implicit (JSON responses via ok/err helpers). Error handling returns structured text but lacks recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Composition is sound, tools are single-responsibility and chainable. Security: no secrets in params (good). Missing: documented output schemas, pagination for list tools, per-item error reporting for batch operations.

• Document output schemas for all tools. Add a 'Returns' section to each tool description or create a separate schema registry. Example: 'Returns: {address: string, canSign: boolean}'.
• Expand descriptions to 100-200 chars. Include WHEN to use the tool and what it returns. E.g., 'Get the agent's AVAX balance on the current network. Returns balance in wei. Call before send_avax to verify sufficient funds.'
• Add tool annotations via MCP SDK. Mark read-only tools with readOnlyHint=true, destructive tools with destructiveHint=true, and idempotent tools with idempotentHint=true.
• Enhance error messages with recovery guidance. Instead of returning raw error text, return structured errors: {error: 'Insufficient balance', suggestion: 'Call get_balance() to check available AVAX', retryable: false}.
• Add pagination to list tools. Include limit (default 20, max 100) and offset/cursor parameters. Return total_count and next_cursor in responses to enable multi-page iteration.