While mobile applications (i.e., apps) are becoming capable of handling various needs from users, their increasing access to sensitive data raises privacy concerns. To address such concerns, existing techniques automatically identify explanatory sentences from app descriptions; however, many sensitive behaviors are not explained in the corresponding app descriptions. There also exist general techniques that translate code to sentences. However, these techniques lack the vocabulary to explain the uses of sensitive data and fail to consider the context (i.e., the app functionalities) of the sensitive behaviors. To address these limitations, we propose DescribeCtx, a context-aware description synthesis approach that trains a neural machine translation model using a large set of popular apps, and generates app-specific descriptions for sensitive behaviors. Specifically, DescribeCtx designs a novel sequence-to-sequence (seq2seq) model that encodes three heterogeneous sources, i.e., vocabularies provided by privacy polices, behavior summary provided by the call graphs in code, and contextual information provided by GUI texts. Our evaluations on 1,292 Android apps show that, compared with existing baselines, the synthesized sentences of DescribeCtx achieve higher prediction accuracy and user ratings with respect to the reference sentences manually identified in the app descriptions.