address comments

docs/en/samples/pre_post_processing/python.md

@@ -29,3 +29,13 @@ For more information, see the [LangChain Middleware documentation](https://docs.
 You can also add model-level (`wrap_model`) and agent-level (`before_agent`, `after_agent`) hooks to intercept messages at different stages of the execution loop. See the [LangChain Middleware documentation](https://docs.langchain.com/oss/python/langchain/middleware/custom#wrap-style-hooks) for details on these additional hook types.
 {{% /tab %}}
 {{< /tabpane >}}
+
+## Results
+
+The output should look similar to the following. Note that exact responses may vary due to the non-deterministic nature of LLMs and differences between orchestration frameworks.
+
+```
+AI: Booking Confirmed! You earned 500 Loyalty Points with this stay.
+
+AI: Error: Maximum stay duration is 14 days.
+```

docs/en/samples/pre_post_processing/python/langchain/agent.py

@@ -47,7 +47,13 @@ async def enforce_business_rules(request, handler):
             except ValueError:
                 pass  # Ignore invalid date formats
 
-    return await handler(request)
+    # PRE: Code here runs BEFORE the tool execution
+    
+    # EXEC: Execute the tool (or next middleware)
+    result = await handler(request)
+
+    # POST: Code here runs AFTER the tool execution
+    return result
 
 
 # Post processing
@@ -58,8 +64,12 @@ async def enrich_response(request, handler):
     Adds loyalty points information to successful bookings.
     Standardizes output format.
     """
+    # PRE: Code here runs BEFORE the tool execution
+    
+    # EXEC: Execute the tool (or next middleware)
     result = await handler(request)
 
+    # POST: Code here runs AFTER the tool execution
     if isinstance(result, ToolMessage):
         content = str(result.content)
         tool_name = request.tool_call["name"]
@@ -79,6 +89,7 @@ async def main():
             system_prompt=system_prompt,
             model=model,
             tools=tools,
+            # add any pre and post processing methods
             middleware=[enforce_business_rules, enrich_response],
         )