add description

Author: shohei1029

articles/machine-learning/how-to-inference-server-http.md

@@ -34,10 +34,10 @@ The following table provides an overview of scenarios to help you choose what wo
 
 | Scenario                                                                | Inference HTTP Server | Local endpoint |
 | ----------------------------------------------------------------------- | --------------------- | -------------- |
-| Update local Python environment **without** Docker image rebuild       | Yes                   | No             |
+| Update local Python environment **without** Docker image rebuild        | Yes                   | No             |
 | Update scoring script                                                   | Yes                   | Yes            |
 | Update deployment configurations (deployment, environment, code, model) | No                    | Yes            |
-| Integrate VS Code Debugger                                            | Yes                   | Yes            |
+| Integrate VS Code Debugger                                              | Yes                   | Yes            |
 
 By running the inference HTTP server locally, you can focus on debugging your scoring script without being affected by the deployment container configurations.
 
@@ -61,7 +61,10 @@ python -m pip install azureml-inference-server-http
 ```
 
 ## Debug your scoring script locally
-### Understand the server behavior with a dummy scoring script
+
+To debug your scoring script locally, you can test how the server behaves with a dummy scoring script, use VS Code to debug with the [azureml-inference-server-http](https://pypi.org/project/azureml-inference-server-http/) package, or test the server with an actual scoring script, model file, and environment file in our examples.
+
+### Test the server behavior with a dummy scoring script
 1. Create a directory to hold your files:
 
     ```bash