diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py
index 75b198e115905..7e58069e2c22d 100644
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -156,11 +156,13 @@ def add_cli_args(
                             type=int,
                             default=EngineArgs.swap_space,
                             help='CPU swap space size (GiB) per GPU')
-        parser.add_argument('--gpu-memory-utilization',
-                            type=float,
-                            default=EngineArgs.gpu_memory_utilization,
-                            help='the percentage of GPU memory to be used for '
-                            'the model executor')
+        parser.add_argument(
+            '--gpu-memory-utilization',
+            type=float,
+            default=EngineArgs.gpu_memory_utilization,
+            help='the fraction of GPU memory to be used for '
+            'the model executor, which can range from 0 to 1.'
+            'If unspecified, will use the default value of 0.9.')
         parser.add_argument('--max-num-batched-tokens',
                             type=int,
                             default=EngineArgs.max_num_batched_tokens,