We analyze teachers' written feedback to students in an online learning environment, specifically a setting in which high school students in Uruguay are learning English as a foreign language. How complex should teachers' feedback be? Should it be adapted to each student's English proficiency level? How does teacher feedback affect the probability of engaging the student in a conversation? To explore these questions, we conducted both parametric (multilevel modeling) and non-parametric (bootstrapping) analyses of 27,627 messages exchanged between 35 teachers and 1074 students in 2017 and 2018. Our results suggest: (1) Teachers should adapt their feedback complexity to their students' English proficiency level. Students who receive feedback that is too complex or too basic for their level post 13-15% fewer comments than those who receive adapted feedback. (2) Feedback that includes a question is associated with higher odds-ratio (17.5-19) of engaging the student in conversation. (3) For students with low English proficiency, slow turnaround (feedback after 1 week) reduces this odds ratio by 0.7. These results have potential implications for online platforms offering foreign language learning services, in which it is crucial to give the best possible learning experience while judiciously allocating teachers' time. [For the full proceedings, see ED599096.]