diff --git a/metagpt/prompts/di/role_zero.py b/metagpt/prompts/di/role_zero.py
index a703b1d41..e04155fe8 100644
--- a/metagpt/prompts/di/role_zero.py
+++ b/metagpt/prompts/di/role_zero.py
@@ -119,17 +119,11 @@ END_COMMAND = """
 ```
 """
 
-SUMMARY_TROUBLE = """
-You are repeating the same action.
-Please summarize what is confusing or troubling you, and tell me directly.
-Do not output any commands.
-Your response must be in {language} and should be within 30 words.
-"""
-DUPULICATE_QUESTTION_FORMAT = """
-I meet the following trouble:
-{trouble}
-Could you provide me with some guidance?
-If want to stop, please contain \"<STOP>\" in your guidance.
+SUMMARY_PROBLEM_WHEN_DUPLICATE = """Please directly tell me what is confusing or troubling you. Your response should be in {language} and within 30 words."""
+ASK_HUMAN_GUIDANCE_FORMAT = """
+I am facing the following problem:
+{problem}
+Could you please provide me with some guidance?If you want to stop, please include "<STOP>" in your guidance.
 """
 ASK_HUMAN_COMMAND = [{"command_name": "RoleZero.ask_human", "args": {"question": ""}}]
 
diff --git a/metagpt/roles/di/engineer2.py b/metagpt/roles/di/engineer2.py
index 2404949cb..044ff0afd 100644
--- a/metagpt/roles/di/engineer2.py
+++ b/metagpt/roles/di/engineer2.py
@@ -119,7 +119,7 @@ class Engineer2(RoleZero):
 
         Args:
             path (str): The absolute path of the file to be created.
-            file_description (optional, str): Further hints or notice other than the current task description, must be very concise and can be empty. Defaults to "".
+            file_description (optional, str): "Brief description and important notes of the file content, must be very concise and can be empty. Defaults to "".
         """
         plan_status, _ = self._get_plan_status()
         prompt = WRITE_CODE_PROMPT.format(
diff --git a/metagpt/roles/di/role_zero.py b/metagpt/roles/di/role_zero.py
index a78202378..9fca8f468 100644
--- a/metagpt/roles/di/role_zero.py
+++ b/metagpt/roles/di/role_zero.py
@@ -19,9 +19,9 @@ from metagpt.exp_pool.serializers import RoleZeroSerializer
 from metagpt.logs import logger
 from metagpt.prompts.di.role_zero import (
     ASK_HUMAN_COMMAND,
+    ASK_HUMAN_GUIDANCE_FORMAT,
     CMD_PROMPT,
     DETECT_LANGUAGE_PROMPT,
-    DUPULICATE_QUESTTION_FORMAT,
     END_COMMAND,
     JSON_REPAIR_PROMPT,
     QUICK_RESPONSE_SYSTEM_PROMPT,
@@ -31,8 +31,8 @@ from metagpt.prompts.di.role_zero import (
     REGENERATE_PROMPT,
     REPORT_TO_HUMAN_PROMPT,
     ROLE_INSTRUCTION,
+    SUMMARY_PROBLEM_WHEN_DUPLICATE,
     SUMMARY_PROMPT,
-    SUMMARY_TROUBLE,
     SYSTEM_PROMPT,
 )
 from metagpt.roles import Role
@@ -401,9 +401,9 @@ class RoleZero(Role):
                     logger.warning(f"Duplicate response detected: {command_rsp}")
                     return END_COMMAND
                 trouble_content = await self.llm.aask(
-                    req + [UserMessage(content=SUMMARY_TROUBLE.format(language=self.respond_language))]
+                    req + [UserMessage(content=SUMMARY_PROBLEM_WHEN_DUPLICATE.format(language=self.respond_language))]
                 )
-                ASK_HUMAN_COMMAND[0]["args"]["question"] = DUPULICATE_QUESTTION_FORMAT.format(trouble=trouble_content)
+                ASK_HUMAN_COMMAND[0]["args"]["question"] = ASK_HUMAN_GUIDANCE_FORMAT.format(trouble=trouble_content)
                 ask_human_command = "```json\n" + json.dumps(ASK_HUMAN_COMMAND, indent=4, ensure_ascii=False) + "\n```"
                 return ask_human_command
             # Try correction by self