diff --git a/iobber/chunker.py b/iobber/chunker.py
index 27643d001f5dd1cc903e5c82d73fecefb04ddcee..1ba5019e074ae6f2624e731ec8c22aabe85390cb 100644
--- a/iobber/chunker.py
+++ b/iobber/chunker.py
@@ -59,7 +59,13 @@ class Chunker:
 	channels during one run, as specified in layer definitions.
 	Layers are applied sequentially. A layer defines a set of channels
 	that are dealt with at a time.
-	TODO doc
+	A chunker is parametrised with an INI file, defining layers and settings
+	and a WCCL file defing features to be used by the underlying classifier.
+	A new chunker object should be called either load_model to become a
+	functional chunker or train_and_save to infer chunking model from the
+	training data. NOTE: after training the chunker object is still not
+	ready for performance, i.e. the trained model is just saved to disk
+	and requires loading.
 	"""
 	
 	def __init__(self, config_path, data_dir, verbose = False):