diff --git a/R/nullmodel.R b/R/nullmodel.R
index ad832f19e..36deaaf72 100644
--- a/R/nullmodel.R
+++ b/R/nullmodel.R
@@ -127,9 +127,18 @@ predict.nullmodel <- function (object, new_data = NULL, type  = NULL, ...) {
 
 #' Null model
 #'
+#' Fit a single mean or largest class model. `null_model()` is the user-facing
+#' function that relies on the underlying computational function, `nullmodel()`.
+#'
 #' `null_model()` defines a simple, non-informative model. It doesn't have any
 #'  main arguments. This function can fit classification and regression models.
 #'
+#' `null_model()` emulates other model building functions, but returns the
+#' simplest model possible given a training set: a single mean for numeric
+#' outcomes and the most prevalent class for factor outcomes. When class
+#' probabilities are requested, the percentage of the training set samples with
+#' the most prevalent class is returned.
+#'
 #' @param mode A single character string for the type of model. The only
 #' possible values for this model are `"regression"` and `"classification"`.
 #' @param engine A single character string specifying what computational engine
diff --git a/man/null_model.Rd b/man/null_model.Rd
index aa16a4230..c12a03f1f 100644
--- a/man/null_model.Rd
+++ b/man/null_model.Rd
@@ -15,8 +15,18 @@ to use for fitting. Possible engines are listed below. The default for this
 model is \code{"parsnip"}.}
 }
 \description{
+Fit a single mean or largest class model. \code{null_model()} is the user-facing
+function that relies on the underlying computational function, \code{nullmodel()}.
+}
+\details{
 \code{null_model()} defines a simple, non-informative model. It doesn't have any
 main arguments. This function can fit classification and regression models.
+
+\code{null_model()} emulates other model building functions, but returns the
+simplest model possible given a training set: a single mean for numeric
+outcomes and the most prevalent class for factor outcomes. When class
+probabilities are requested, the percentage of the training set samples with
+the most prevalent class is returned.
 }
 \section{Engine Details}{
 Engines may have pre-set default arguments when executing the model fit