Effective physical human-robot interaction requires systems that are not only adaptable to user preferences but also transparent about their actions. This paper introduces a system for bidirectional human-robot communication in the context of physically assistive scenarios. Our method empowers users with the ability to modify a robot's planned trajectory--including its position, velocity, and force--in real time using natural language. We utilize a large language model (LLM) to interpret any trajectory modifications implied by user commands in the context of the planned motion and conversation history. Importantly, our system provides verbal feedback in response to the user, either assuring any resulting changes or posing a clarifying question. We evaluated our method in a user study with 18 older adults across three assistive tasks, comparing our bidirectional approach to a unidirectional ablation (modifications without feedback) and a baseline without modifications. Results show that participants successfully used the system to modify trajectories in real time. Moreover, the bidirectional feedback led to significantly higher ratings of interactivity, transparency, and grounding, demonstrating that the robot's verbal response is critical for creating a more intuitive user experience.