diff --git a/comfy_extras/nodes_scail.py b/comfy_extras/nodes_scail.py
index 76c15f07d..a740442de 100644
--- a/comfy_extras/nodes_scail.py
+++ b/comfy_extras/nodes_scail.py
@@ -134,12 +134,12 @@ class WanSCAILToVideo(io.ComfyNode):
                 io.Int.Input("batch_size", default=1, min=1, max=4096),
                 io.Image.Input("pose_video", optional=True, tooltip="Video used for pose conditioning. Will be downscaled to half the resolution of the main video."),
                 io.Image.Input("pose_video_mask", optional=True, tooltip="SCAIL-2 only. Colored per-identity SAM3 mask video at the same resolution as pose_video."),
-                io.Boolean.Input("replacement_mode", default=False, optional=True, tooltip="SCAIL-2 only. False = Animation Mode (mask bg black). True = Replacement Mode (mask bg white; the reference is composited onto black using ref_image_mask as an alpha matte). Must match how the colored masks were rendered."),
+                io.Boolean.Input("replacement_mode", default=False, optional=True, tooltip="SCAIL-2 only. False = Animation Mode (pose_video_mask should have black background). True = Replacement Mode (pose_video_mask should have white background)."),
                 io.Float.Input("pose_strength", default=1.0, min=0.0, max=10.0, step=0.01, tooltip="Strength of the pose latent."),
-                io.Float.Input("pose_start", default=0.0, min=0.0, max=1.0, step=0.01, tooltip="Start step to use pose conditioning."),
-                io.Float.Input("pose_end", default=1.0, min=0.0, max=1.0, step=0.01, tooltip="End step to use pose conditioning."),
+                io.Float.Input("pose_start", default=0.0, min=0.0, max=1.0, step=0.01, tooltip="Start step of the pose conditioning."),
+                io.Float.Input("pose_end", default=1.0, min=0.0, max=1.0, step=0.01, tooltip="End step of the pose conditioning."),
                 io.Image.Input("reference_image", optional=True, tooltip="Reference image, for multiple references composite all on single image."),
-                io.Image.Input("reference_image_mask", optional=True, tooltip="SCAIL-2 only. Single-frame colored mask at the same resolution as reference_image."),
+                io.Image.Input("reference_image_mask", optional=True, tooltip="SCAIL-2 only. Colored reference mask at the same resolution as reference_image."),
                 io.ClipVisionOutput.Input("clip_vision_output", optional=True, tooltip="CLIP vision features for conditioning. Model is trained with stretch resize to aspect ratio."),
                 io.Int.Input("video_frame_offset", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1, tooltip="Cumulative output frame this chunk begins at. Wire from the previous chunk's video_frame_offset output."),
                 io.Int.Input("previous_frame_count", default=5, min=1, max=nodes.MAX_RESOLUTION, step=4, tooltip="Tail frames of previous_frames to anchor. SCAIL-2 trained at 5 (81-frame chunks, 76-frame step)."),