diff --git a/tools/README.md b/tools/README.md
index 8b5840e..502f899 100644
--- a/tools/README.md
+++ b/tools/README.md
@@ -37,4 +37,14 @@ extract-doc-links enp_DE.tsv  enp_DE-urls.tsv
 
 By loading the annotated TSV as well as the url mapping file into 
 ner.edith, you will be able to jump directly to the original image
-where the full text has been extracted from.
\ No newline at end of file
+where the full text has been extracted from.
+
+# PAGE-XML to TSV Transformation
+
+## Usage:
+
+Create a TSV file from OCR in PAGE-XML format (with word segmentation):
+
+```
+python page2tsv.py PAGE.xml > PAGE.tsv
+```