Letters of recommendation from school counselors are required to apply to most selective universities. We use cutting-edge natural language processing techniques to algorithmically analyze a national dataset of over 600,000 student applications and counselor recommendation letters submitted through the Common Application. We examine how the length and topical content of letters (e.g., sentences about Personal Qualities, Athletics, Intellectual Promise, etc.) relate to race/ethnicity, sex, and proxies for socioeconomic status. We explore whether differences in letter characteristics persist when accounting for additional student, school, and counselor characteristics; letters written by the same counselor; and for students with higher standardized test scores. We found noteworthy naïve differences in letter length and content across nearly all demographic groups, many reflecting known inequities (e.g., longer letters and more sentences on Personal Qualities for private school students). However, the ultimate implications of these patterns hinge on exactly "how" and "when" letters are used in admissions processes (e.g., are letters evaluated at face value across all students, or are they mostly compared to other letters from the same high school or counselor?). Findings reflect the importance of reading letters and applications in the context of structural opportunity, although they do not point to a clear recommendation on whether institutions should keep or discard requirements related to letters or standardized tests. We discuss additional implications and recommendations for admissions policy and practice.