fix(dualagent): improve no-tool-call feedback with explicit XML format reminder

When the LLM fails to emit a tool_call XML block, the feedback now includes
the exact XML format expected with a concrete example for json.validate.
This helps smaller models understand the exact output format required.

ts/smartagent.classes.dualagent.ts

@@ -319,9 +319,27 @@ export class DualAgentOrchestrator {
       const proposals = this.driver.parseToolCallProposals(driverResponse.content);
 
       if (proposals.length === 0) {
-        // No tool calls, continue the conversation
+        // No tool calls found - remind the model of the exact XML format
         driverResponse = await this.driver.continueWithMessage(
-          'Please either use a tool to make progress on the task, or indicate that the task is complete with <task_complete>summary</task_complete>.'
+          `No valid tool call was found in your response. To use a tool, you MUST output the exact XML format:
+
+<tool_call>
+  <tool>tool_name</tool>
+  <action>action_name</action>
+  <params>{"param1": "value1"}</params>
+</tool_call>
+
+For example, to validate JSON:
+<tool_call>
+  <tool>json</tool>
+  <action>validate</action>
+  <params>{"jsonString": "{\\"key\\":\\"value\\"}", "requiredFields": ["key"]}</params>
+</tool_call>
+
+Or to complete the task:
+<task_complete>your final JSON output here</task_complete>
+
+Please output the exact XML format above.`
         );
         this.conversationHistory.push(driverResponse);
         continue;