diff --git a/toolkit.py b/toolkit.py
index 1a27649850593b31c9dae9673222b13cd4a3700d..5a6aa8a59e1866dd33d0f453ce06777b0b26cfee 100755
--- a/toolkit.py
+++ b/toolkit.py
@@ -991,6 +991,10 @@ class ClassificationProject(object):
 
 
     def predict(self, x, mode=None):
+        """
+        Calculate the scores for a (transformed) array of input values.
+        If the array is not transformed, use `evaluate` instead
+        """
         if mode is None:
             # normal output - after activation function output layer
             return self.model.predict(x)
@@ -1010,6 +1014,10 @@ class ClassificationProject(object):
 
 
     def evaluate(self, x_eval, mode=None):
+        """
+        Calculate the scores for an array of input values.
+        All nescessary transformations are applied.
+        """
         logger.debug("Evaluate score for {}".format(x_eval))
         x_eval = self.transform(x_eval)
         logger.debug("Evaluate for transformed array: {}".format(x_eval))