diff --git a/pr_agent/settings/pr_description_prompts.toml b/pr_agent/settings/pr_description_prompts.toml
index 76e8dd45..33d7e01e 100644
--- a/pr_agent/settings/pr_description_prompts.toml
+++ b/pr_agent/settings/pr_description_prompts.toml
@@ -18,11 +18,13 @@ You must use the following JSON schema to format your answer:
       "type": "string",
       "description": "an informative and concise description of the PR"
   },
-  "PR Walkthrough": {
+  "PR Main Files Walkthrough": {
       "type": "string",
-      "description": "a walkthrough of the PR changes. Review file by file, in bullet points, and shortly describe the changes in each file. Format: -`filename`: description of changes\n..."
+      "description": "a walkthrough of the PR changes. Review main files, in bullet points, and shortly describe the changes in each file (up to 10 most important files). Format: -`filename`: description of changes\n..."
   }
 }
+
+Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
 """
 
 user="""PR Info:
diff --git a/pr_agent/tools/pr_description.py b/pr_agent/tools/pr_description.py
index be237254..8ae01791 100644
--- a/pr_agent/tools/pr_description.py
+++ b/pr_agent/tools/pr_description.py
@@ -72,10 +72,10 @@ class PRDescription:
         #     markdown_text += f"{value}\n\n"
         for key, value in data.items():
             markdown_text += f"{key}:\n"
-            if 'walkthrough' not in key.lower():
-                markdown_text += f"**{value}**\n"
+            if 'walkthrough' in key.lower():
+                markdown_text += f"{value}\n"
             else:
-                markdown_text += f"{value}\n\n___\n"
+                markdown_text += f"**{value}**\n\n___\n"
         if settings.config.verbosity_level >= 2:
             logging.info(f"markdown_text:\n{markdown_text}")
         return markdown_text