fix: Fix unclear error messages for SageMaker Pipelines

src/sagemaker/workflow/entities.py

@@ -85,8 +85,11 @@ def __str__(self):
         """Override built-in String function for PipelineVariable"""
         raise TypeError(
             "Pipeline variables do not support __str__ operation. "
-            "Please use `.to_string()` to convert it to string type in execution time"
-            "or use `.expr` to translate it to Json for display purpose in Python SDK."
+            "If you are trying to use a pipeline variable in an Estimator, Processor or Model "
+            "object, please make sure the object is built with a PipelineSession object."
+            "If you are trying to convert a pipeline variable of any type into a pipeline variable "
+            "of string type, please use `.to_string()` method."
+            "Use `.expr` method to display the expression structure of the pipeline variable."
         )
 
     def __int__(self):

src/sagemaker/workflow/model_step.py

@@ -124,8 +124,9 @@ def __init__(
                 Session.create_model.__name__,
                 Session.create_model_package_from_containers.__name__,
             },
-            error_message="The step_args of ModelStep must be obtained from model.create() "
-            "or model.register(). For more, see: https://sagemaker.readthedocs.io/en/stable/"
+            error_message="The step_args of ModelStep must be obtained from the create method "
+            "or register method of a Model object and the Model object must be built with "
+            "PipelineSession. For more, see: https://sagemaker.readthedocs.io/en/stable/"
             "amazon_sagemaker_model_building_pipeline.html#model-step",
         )
         if not (step_args.create_model_request is None) ^ (