diff --git a/crates/bsk-cli/skill/SKILL.md b/crates/bsk-cli/skill/SKILL.md
index 2b870c2..e098730 100644
--- a/crates/bsk-cli/skill/SKILL.md
+++ b/crates/bsk-cli/skill/SKILL.md
@@ -80,7 +80,7 @@ Prefer `@eN` refs from the latest snapshot over raw CSS selectors. Use `--ref` /
 
 When VOM renders `[hover first: …]` on an element, the listed items are not currently clickable refs. Run `bsk hover <that-ref> --session <id>`, then immediately run `bsk snapshot` or `bsk observe` again and click the newly visible menu item ref. Do not click the trigger itself unless the user explicitly wants the trigger action.
 
-When `bsk observe` renders `@eN surface ... [visual-only; ...]`, the ref identifies a rendered canvas surface, not an interactable DOM control. Use `bsk screenshot --ref @eN --session <id>` to inspect its visible crop. Do not pass a visual surface ref to click, fill, hover, or select; those commands intentionally reject screenshot-only refs.
+When `bsk observe` renders `@eN surface ... [visual-only; requires=image-understanding; ...]`, the ref identifies rendered canvas content that is not represented by the text observation, not an interactable DOM control. Keep using any reliable DOM/AX text and controls that appear alongside it. If you can actually inspect image output, use `bsk screenshot --ref @eN --session <id>` to obtain the visible crop. If you lack multimodal or image-reading capability, do not take a screenshot and pretend to know its contents, and never guess coordinates; tell the user that they need to switch to a model with image-understanding capability. Do not pass a visual surface ref to click, fill, hover, or select; those commands intentionally reject screenshot-only refs.
 
 ## Observation priority
 
diff --git a/crates/bsk-cli/src/cli/render_error.rs b/crates/bsk-cli/src/cli/render_error.rs
index bd5db93..d7b2992 100644
--- a/crates/bsk-cli/src/cli/render_error.rs
+++ b/crates/bsk-cli/src/cli/render_error.rs
@@ -232,7 +232,7 @@ pub fn info_for_error(code: ErrorCode, data: Option<&serde_json::Value>) -> Rend
         (ErrorCode::PermissionDenied, reason::REF_CAPABILITY_DENIED) => RenderInfo {
             summary: "snapshot ref does not support this operation",
             hint: Some(
-                "visual surface refs are screenshot-only; run `bsk screenshot --ref <ref> --session <id>`",
+                "visual surface refs are screenshot-only; inspect `bsk screenshot --ref <ref> --session <id>` with image-understanding capability",
             ),
             exit_code: base.exit_code,
         },
diff --git a/packages/dsh-plugin-browserskill/src/tools.ts b/packages/dsh-plugin-browserskill/src/tools.ts
index b848b6b..cf1ba68 100644
--- a/packages/dsh-plugin-browserskill/src/tools.ts
+++ b/packages/dsh-plugin-browserskill/src/tools.ts
@@ -489,8 +489,9 @@ function defineBrowserOperations(deps: ToolDeps, register: DefinitionRegistrar):
       ? "Capture an indented aria-tree snapshot of the session's active tab. Interactive elements " +
         "carry @eN refs for browser_interact actions. Prefer browser_inspect action=observe for a richer semantic view."
       : "Produce a semantic VOM observation of the session's active tab (roles, states, perception " +
-        "probes) with @eN refs for browser_interact actions. Visual surface refs are screenshot-only; " +
-        "DOM refs support interaction. Read-only: never submits input.";
+        "probes) with @eN refs for browser_interact actions. Visual-only surfaces require image " +
+        "understanding and their refs are screenshot-only; keep using any DOM/AX semantics rendered " +
+        "alongside them. Read-only: never submits input.";
     register(
       defineTool({
         name,
@@ -753,8 +754,11 @@ function defineBrowserOperations(deps: ToolDeps, register: DefinitionRegistrar):
       name: "inspect.screenshot",
       description:
         "Capture a PNG screenshot of the session's active tab, or crop to a snapshot ref element. " +
-        "This is the supported operation for visual surface refs emitted by browser_observe. Returns " +
-        "the image itself when the deployment supports image input, otherwise a file path.",
+        "This is the supported operation for visual surface refs emitted by inspect.observe. Only use " +
+        "it to interpret a visual-only surface when you can inspect image output. If you lack multimodal " +
+        "or image-reading capability, tell the user to switch to a model with image understanding; do " +
+        "not guess content or coordinates. " +
+        "Returns the image itself when the deployment supports image input, otherwise a file path.",
       parameters: {
         session: SESSION_PARAM,
         ref: {
diff --git a/packages/vom/src/__tests__/render.test.ts b/packages/vom/src/__tests__/render.test.ts
index 08f7350..84a6731 100644
--- a/packages/vom/src/__tests__/render.test.ts
+++ b/packages/vom/src/__tests__/render.test.ts
@@ -48,7 +48,7 @@ describe("renderVom single-layer page", () => {
     const out = renderVom(input);
 
     expect(out.text).toContain(
-      '@e1 surface "Data grid" [rendering=canvas; layers=2; visual-only; use: bsk screenshot --ref @e1]',
+      '@e1 surface "Data grid" [rendering=canvas; layers=2; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
     );
     expect(out.refs).toContainEqual(
       expect.objectContaining({
@@ -77,7 +77,7 @@ describe("renderVom single-layer page", () => {
     const out = renderVom(input);
 
     expect(out.text).toContain(
-      '@e1 surface "canvas visual surface" [rendering=canvas; visual-only; use: bsk screenshot --ref @e1]',
+      '@e1 surface "canvas visual surface" [rendering=canvas; visual-only; requires=image-understanding; use: bsk screenshot --ref @e1]',
     );
     expect(out.refs).toContainEqual(
       expect.objectContaining({
diff --git a/packages/vom/src/render.ts b/packages/vom/src/render.ts
index 53076d0..92a151a 100644
--- a/packages/vom/src/render.ts
+++ b/packages/vom/src/render.ts
@@ -763,7 +763,7 @@ function emitVisualEntries(parentId: number | null, depth: number, state: Render
     const ref = `e${state.nextRef}`;
     const label = cleaned(surface.label) ?? `${surface.renderingKind} visual surface`;
     const layers = surface.memberCount > 1 ? `; layers=${surface.memberCount}` : "";
-    const line = `${"  ".repeat(depth)}@${ref} surface ${JSON.stringify(label)} [rendering=${surface.renderingKind}${layers}; visual-only; use: bsk screenshot --ref @${ref}]`;
+    const line = `${"  ".repeat(depth)}@${ref} surface ${JSON.stringify(label)} [rendering=${surface.renderingKind}${layers}; visual-only; requires=image-understanding; use: bsk screenshot --ref @${ref}]`;
     const nextTokens = state.tokens + estimateTokens(line);
     if (nextTokens > state.maxTokens) {
       state.truncated = true;
diff --git a/skill/SKILL.md b/skill/SKILL.md
index 2b870c2..e098730 100644
--- a/skill/SKILL.md
+++ b/skill/SKILL.md
@@ -80,7 +80,7 @@ Prefer `@eN` refs from the latest snapshot over raw CSS selectors. Use `--ref` /
 
 When VOM renders `[hover first: …]` on an element, the listed items are not currently clickable refs. Run `bsk hover <that-ref> --session <id>`, then immediately run `bsk snapshot` or `bsk observe` again and click the newly visible menu item ref. Do not click the trigger itself unless the user explicitly wants the trigger action.
 
-When `bsk observe` renders `@eN surface ... [visual-only; ...]`, the ref identifies a rendered canvas surface, not an interactable DOM control. Use `bsk screenshot --ref @eN --session <id>` to inspect its visible crop. Do not pass a visual surface ref to click, fill, hover, or select; those commands intentionally reject screenshot-only refs.
+When `bsk observe` renders `@eN surface ... [visual-only; requires=image-understanding; ...]`, the ref identifies rendered canvas content that is not represented by the text observation, not an interactable DOM control. Keep using any reliable DOM/AX text and controls that appear alongside it. If you can actually inspect image output, use `bsk screenshot --ref @eN --session <id>` to obtain the visible crop. If you lack multimodal or image-reading capability, do not take a screenshot and pretend to know its contents, and never guess coordinates; tell the user that they need to switch to a model with image-understanding capability. Do not pass a visual surface ref to click, fill, hover, or select; those commands intentionally reject screenshot-only refs.
 
 ## Observation priority