diff --git a/docs/figures/gpu_utilization.png b/docs/figures/gpu_utilization.png
index bde2d88..b80e7fb 100644
Binary files a/docs/figures/gpu_utilization.png and b/docs/figures/gpu_utilization.png differ
diff --git a/scripts/analysis/plot_gpu_utilization.py b/scripts/analysis/plot_gpu_utilization.py
index 7dc81d9..e6d2e3e 100644
--- a/scripts/analysis/plot_gpu_utilization.py
+++ b/scripts/analysis/plot_gpu_utilization.py
@@ -136,7 +136,7 @@ def main() -> None:
     bar_colors = [KVC_P_COLOR, KVC_D_COLOR, KVC_D_COLOR, KVC_D_COLOR,
                   DP_COLOR, DP_COLOR, DP_COLOR, DP_COLOR]
 
-    fig, axes = plt.subplots(1, 2, figsize=(15, 6.5))
+    fig, axes = plt.subplots(1, 2, figsize=(15, 7.0))
     x = np.arange(len(all_gpus))
 
     # -- Left: per-GPU request count ----------------------------------
@@ -148,20 +148,24 @@ def main() -> None:
     ax.set_xticks(x)
     ax.set_xticklabels(labels, fontsize=9.5)
     ax.set_ylabel("Number of requests touching this GPU", fontsize=11)
-    ax.set_title("Per-GPU request count\n(naïve view: P seems idle)", fontsize=12, pad=10)
+    # Headroom for the annotation: extend ylim 35% above tallest bar
+    ax.set_ylim(0, max(counts) * 1.40)
+    ax.set_title("Per-GPU request count\n(naïve view: P seems idle)",
+                 fontsize=12, pad=24)
     ax.grid(axis="y", linestyle=":", alpha=0.4)
     ax.set_axisbelow(True)
 
     # Annotate: KVC P GPU is "low frequency"
+    # Place in upper-right area (over DP group) so it doesn't sit on KVC D bars
     p_idx = 0
-    p_pct = counts[p_idx] / sum(counts[:4]) * 100  # vs KVC total
     ax.annotate(
         f"P GPU only sees\n"
         f"{counts[p_idx]:,} requests\n"
-        f"({counts[p_idx]/len(kvc)*100:.1f}% of total)",
+        f"({counts[p_idx]/len(kvc)*100:.1f}% of all KVC requests)",
         xy=(p_idx, counts[p_idx]),
-        xytext=(p_idx + 0.6, max(counts) * 0.55),
-        fontsize=9, color=KVC_P_COLOR, fontweight="bold",
+        xytext=(2.4, max(counts) * 1.20),
+        fontsize=10, color=KVC_P_COLOR, fontweight="bold", ha="center",
+        bbox=dict(facecolor="white", edgecolor=KVC_P_COLOR, alpha=0.92, pad=4),
         arrowprops=dict(arrowstyle="->", color=KVC_P_COLOR, lw=1.0),
     )
 
@@ -185,31 +189,42 @@ def main() -> None:
     ax.set_xticks(x)
     ax.set_xticklabels(labels, fontsize=9.5)
     ax.set_ylabel("Compute tokens (millions)", fontsize=11)
+    # Headroom for the annotation
+    ax.set_ylim(0, max(total_M) * 1.45)
     ax.set_title("Per-GPU compute work\n(work view: P is comparable to each D)",
-                 fontsize=12, pad=10)
+                 fontsize=12, pad=24)
     ax.grid(axis="y", linestyle=":", alpha=0.4)
     ax.set_axisbelow(True)
+    # Legend placed at upper-left where bars are tallest is fine after raising ylim
     ax.legend(loc="upper left", fontsize=10, framealpha=0.95)
 
-    # Annotate: KVC P GPU does similar work to each D
+    # Annotate: KVC P GPU does similar work to each D.
+    # Place over DP region (right side) so it doesn't sit on KVC D bars.
     ax.annotate(
-        f"P GPU does {total_M[p_idx]:.2f}M tokens of\n"
-        f"prefill — comparable per-GPU\n"
-        f"load to each KVC D worker",
+        f"P GPU does {total_M[p_idx]:.2f}M tokens of prefill\n"
+        f"— comparable per-GPU load to each KVC D worker\n"
+        f"(KVC D avg = {np.mean(total_M[1:4]):.2f}M)",
         xy=(p_idx, total_M[p_idx]),
-        xytext=(p_idx + 0.6, max(total_M) * 0.62),
-        fontsize=9, color=KVC_P_COLOR, fontweight="bold",
+        xytext=(5.5, max(total_M) * 1.30),
+        fontsize=10, color=KVC_P_COLOR, fontweight="bold", ha="center",
+        bbox=dict(facecolor="white", edgecolor=KVC_P_COLOR, alpha=0.92, pad=4),
         arrowprops=dict(arrowstyle="->", color=KVC_P_COLOR, lw=1.0),
     )
 
-    # Separator + group labels
+    # Separator + group labels (placed in axes-fraction coords, below subplot
+    # title at pad=24 we now have safe room for these at y_axes_frac ≈ 1.02)
     for ax in axes:
         ax.axvline(3.5, color="gray", linestyle="--", linewidth=1.0, alpha=0.5)
-        ymin, ymax = ax.get_ylim()
-        ax.text(1.5, ymax * 1.05, "KVC 1P3D", ha="center", fontsize=11,
-                fontweight="bold", color="#444")
-        ax.text(5.5, ymax * 1.05, "DP 4-way CA", ha="center", fontsize=11,
-                fontweight="bold", color="#444")
+        ax.text(0.25, 1.02, "KVC 1P3D",
+                transform=ax.transAxes, ha="center", va="bottom",
+                fontsize=11.5, fontweight="bold", color="#444",
+                bbox=dict(facecolor="#F2F2F2", edgecolor="#888",
+                          alpha=0.85, pad=3))
+        ax.text(0.75, 1.02, "DP 4-way CA",
+                transform=ax.transAxes, ha="center", va="bottom",
+                fontsize=11.5, fontweight="bold", color="#444",
+                bbox=dict(facecolor="#F2F2F2", edgecolor="#888",
+                          alpha=0.85, pad=3))
 
     fig.suptitle(
         "Per-GPU utilization: \"is KVC's prefill GPU wasted?\"\n"