Enhance LlmController with detailed data analysis workflow and proactive tool usage

- Expanded system message to include a comprehensive critical analysis workflow for data retrieval and analysis.
- Added specific guidelines for retrieving complete data and providing in-depth analysis for backtests, bundles, and indicators.
- Emphasized the importance of proactive engagement and multiple tool iterations to ensure thorough responses.
- Updated tool usage instructions to improve clarity and effectiveness in user interactions.

src/Managing.Api/Controllers/LlmController.cs

@@ -250,12 +250,32 @@ public class LlmController : BaseController
 
             TOOL USAGE:
             - Use tools ONLY for system operations: backtesting, retrieving user data, or real-time market data
-            - When users ask about their data ("best backtest", "my indicators", "my backtests"), use tools proactively with smart defaults:
+            - When users ask about their data, use tools proactively with smart defaults:
               * "Best backtest" → get_backtests_paginated(sortBy='Score', sortOrder='desc', pageSize=10)
               * "My indicators" → list_indicators()
               * "Recent backtests" → get_backtests_paginated(sortOrder='desc', pageSize=20)
-            - Execute multiple tool iterations to provide complete answers
-            - Only ask for clarification when truly necessary
+              * "Bundle backtest analysis" → analyze_bundle_backtest(bundleRequestId='X')
+
+            CRITICAL ANALYSIS WORKFLOW (APPLIES TO ALL DATA):
+            1. RETRIEVE COMPLETE DATA:
+               - When asked to analyze ANY entity, ALWAYS fetch FULL details first (never rely on summary/paginated data alone)
+               - Backtests: get_backtest_by_id() for positions + complete metrics
+               - Bundles: analyze_bundle_backtest() for aggregated statistics
+               - Indicators: get_indicator_info() for detailed specs
+               - Use conversation context: "that X" or "this Y" → extract ID from previous messages
+
+            2. ANALYZE WITH EXPERTISE:
+               After retrieving data, provide comprehensive analysis:
+
+               Backtests: Performance (PnL, growth, ROI), Risk (Sharpe, drawdown), Win rate, Position patterns, Strengths/weaknesses, Recommendations
+               Bundles: Aggregate performance, Best/worst combinations, Optimal parameters, Robustness
+               Indicators: Use cases, Parameter sensitivity, Combination suggestions, Pitfalls
+               General: Compare to benchmarks, Statistical significance, Actionable insights
+
+            3. BE PROACTIVE:
+               - Execute multiple tool iterations for complete data
+               - Interpret data, don't just return it
+               - Only ask for clarification when truly ambiguous
 
             Be concise, accurate, and proactive.
             """;