perf(tools): lower default result sizes to cut response tokens

The default limits let broad queries flood the model context. This
change sets smaller defaults. An explicit parameter still overrides each one.

- file_search: max_results 1000 to 50, context_lines 2 to 0.
- ast_query: max_results 100 to 50.
- ast_query compact output omits the node type unless verbose is set.

On a fixed seven-call suite, response size fell from 198529 to 61960 bytes.

internal/server/handlers_file.go

@@ -51,7 +51,7 @@ func (s *Server) handleFileSearch(ctx context.Context, request mcp.CallToolReque
 	fileTypes := request.GetStringSlice("file_types", nil)
 	ignoreCase := request.GetBool("ignore_case", false)
 	regex := request.GetBool("regex", true)
-	contextLines := request.GetInt("context_lines", 2)
+	contextLines := request.GetInt("context_lines", 0)
 
 	// Consult session prefs for max_results and cluster when not explicitly supplied.
 	prefs := s.sessionPrefs.Load()