diff --git a/vision_agent/agent/vision_agent_prompts.py b/vision_agent/agent/vision_agent_prompts.py
index 45e0310d..1b3d464e 100644
--- a/vision_agent/agent/vision_agent_prompts.py
+++ b/vision_agent/agent/vision_agent_prompts.py
@@ -68,7 +68,7 @@
 1. **Understand and Clarify**: Make sure you understand the task.
 2. **Algorithm/Method Selection**: Decide on the most efficient way.
 3. **Pseudocode Creation**: Write down the steps you will follow in pseudocode.
-4. **Code Generation**: Translate your pseudocode into executable Python code.
+4. **Code Generation**: Translate your pseudocode into executable Python code. Ensure you use correct arguments, remember coordinates are always returned normalized from `vision_agent.tools`.
 5. **Logging**: Log the output of the custom functions that were provided to you from `from vision_agent.tools import *`. Use a debug flag in the function parameters to toggle logging on and off.
 """
 
diff --git a/vision_agent/tools/tools.py b/vision_agent/tools/tools.py
index d0ddcd12..7baa02b6 100644
--- a/vision_agent/tools/tools.py
+++ b/vision_agent/tools/tools.py
@@ -60,8 +60,8 @@ def grounding_dino(
 ) -> List[Dict[str, Any]]:
     """'grounding_dino' is a tool that can detect and count multiple objects given a text
     prompt such as category names or referring expressions. The categories in text prompt
-    are separated by commas or periods. It returns a list and count of bounding boxes,
-    label names and associated probability scores.
+    are separated by commas or periods. It returns a list of bounding boxes with
+    normalized coordinates, label names and associated probability scores.
 
     Parameters:
         prompt (str): The prompt to ground to the image.
@@ -73,7 +73,7 @@ def grounding_dino(
 
     Returns:
         List[Dict[str, Any]]: A list of dictionaries containing the score, label, and
-        bounding box of the detected objects with normalized coordinates
+        bounding box of the detected objects with normalized coordinates between 0 and 1
         (xmin, ymin, xmax, ymax). xmin and ymin are the coordinates of the top-left and
         xmax and ymax are the coordinates of the bottom-right of the bounding box.