Novice programmers often face difficulties when writing code independently. To assist struggling students in writing textual code in Python, we have recently implemented personalized Parsons problems as a pop-up scaffolding. These personalized Parsons problems require lower cognitive load to solve in contrast to the matched write-code problems. Students found them to be engaging and helpful for learning. However, a drawback of using Parsons problems as hints is that students may be able to put the code blocks back in place without fully understanding the rationale of the correct solution. As a result, the learning benefits of such hints are compromised. In this work, we aim to augment the benefits of using personalized Parsons problems as hints. In this poster, we present a design to add multi-level textual explanations to code blocks in Parsons problems generated by a large language model. This design will serve as a foundation for subsequent classroom experiments where we investigate the effectiveness of incorporating textual explanations in Parsons problems to enhance their instructional benefits when used as scaffolding opportunities.