Add system message to LLM requests and improve indicator type resolution

- Introduced a system message in LlmController to clarify that tools are optional for LLM responses, enhancing user guidance.
- Refactored indicator type resolution in IndicatorTools to support fuzzy matching and provide suggestions for invalid types, improving user experience and error handling.
- Updated methods to utilize the new resolution logic, ensuring consistent handling of indicator types across the application.

src/Managing.Api/Controllers/LlmController.cs

@@ -57,6 +57,23 @@ public class LlmController : BaseController
             var availableTools = await _mcpService.GetAvailableToolsAsync();
             request.Tools = availableTools.ToList();
 
+            // Add system message to clarify that tools are optional and the LLM can respond directly
+            // Check if a system message already exists
+            var hasSystemMessage = request.Messages.Any(m => m.Role == "system");
+            if (!hasSystemMessage)
+            {
+                var systemMessage = new LlmMessage
+                {
+                    Role = "system",
+                    Content = "You are a helpful AI assistant with expertise in quantitative finance, algorithmic trading, and financial mathematics. " +
+                              "You can answer questions directly using your knowledge. " +
+                              "Tools are available for specific operations (backtesting, agent management, market data retrieval, etc.) but are optional. " +
+                              "Use tools only when they are needed for the specific task. " +
+                              "For general questions, explanations, calculations, or discussions, respond directly without using tools."
+                };
+                request.Messages.Insert(0, systemMessage);
+            }
+
             // Send chat request to LLM
             var response = await _llmService.ChatAsync(user, request);