screenshot

Previous value: -"Must be true to receive image pixels when detail='image'. Without this flag, detail='image' is blocked and a guidance message is returned instead. Prefer detail='text' / diffMode=true / dotByDot=true first — only set confirmImage=true when visual inspection is genuinely required."New value: +"Embed inline image pixels in the response. detail='image' now returns a cheap by-ref resource_link WITHOUT this flag (it is no longer blocked); confirmImage=true ADDITIONALLY embeds the inline image for immediate vision. detail='som' likewise returns its elements[] + a by-ref resource_link by default; confirmImage=true ADDITIONALLY inlines the annotated SoM bitmap. Prefer detail='text' / diffMode=true / dotByDot=true first — set confirmImage=true only when inline visual inspection is genuinely required."

Previous value: -"Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. BLOCKED unless confirmImage=true is also passed.\n  'som'   — Set-of-Marks image + OCR elements (bypasses UIA entirely). BLOCKED unless confirmImage=true is also passed.\n  'ocr'   — Windows OCR words with screen-pixel clickAt coords (Phase 4: absorbs former screenshot_ocr). Use when UIA returns no actionable elements (WinUI3 custom-drawn UIs, game overlays, PDF viewers). Note: detail='text' auto-falls back to OCR via ocrFallback='auto'; choose detail='ocr' only when forcing OCR unconditionally."New value: +"Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. Returns a cheap by-ref resource_link by default (no inline base64); pass confirmImage=true to ALSO embed the inline image.\n  'som'   — Set-of-Marks elements + annotated image (bypasses UIA entirely). Returns the OCR elements[] plus a cheap by-ref resource_link by default (no inline base64); pass confirmImage=true to ALSO embed the annotated bitmap.\n  'ocr'   — Windows OCR words with screen-pixel clickAt coords (Phase 4: absorbs former screenshot_ocr). Use when UIA returns no actionable elements (WinUI3 custom-drawn UIs, game overlays, PDF viewers). Note: detail='text' auto-falls back to OCR via ocrFallback='auto'; choose detail='ocr' only when forcing OCR unconditionally."

Removed value: -"ja"

Previous value: -"BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Used when detail='text' (OCR fallback) or detail='ocr' (direct OCR)."New value: +"BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Auto-detects from system locale when omitted. Used when detail='text' (OCR fallback) or detail='ocr' (direct OCR)."

Added value: +{
+  "description": "Optional response-shape opt-in. `['envelope']` returns the self-documenting envelope (`_version` / `data` / `as_of` / `confidence`). `['raw']` forces raw shape (overrides DESKTOP_TOUCH_ENVELOPE=1 server default). Default behaviour is raw shape (compat with existing clients).",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "Direct window handle ID (takes precedence over windowTitle). Obtain from get_windows (hwnd field). String type to avoid 64-bit precision issues.",
+  "type": "string"
+}

Previous value: -"Capture only the window whose title contains this string. Prefer over full-screen when target window is known."New value: +"Capture only the window whose title contains this string. Use '@active' for the current foreground window. Prefer over full-screen when target window is known."

Removed value: -"http://json-schema.org/draft-07/schema#"

Added value: +false

Removed value: -{
-  "description": "Stub tool — arguments ignored."
-}

Added value: +{
+  "default": false,
+  "description": "Must be true to receive image pixels when detail='image'. Without this flag, detail='image' is blocked and a guidance message is returned instead. Prefer detail='text' / diffMode=true / dotByDot=true first — only set confirmImage=true when visual inspection is genuinely required.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Response detail level (omit to let the server pick a smart default):\n  omitted — auto: 'image' when dotByDot/region/displayId is specified, else 'meta'\n  'meta'  — window title + screen region only (~20 tok/window, cheapest)\n  'text'  — UIA element tree as JSON with text values (~100-300 tok/window, no image)\n  'image' — actual screenshot pixels. BLOCKED unless confirmImage=true is also passed.",
+  "enum": [
+    "meta",
+    "text",
+    "image"
+  ],
+  "type": "string"
+}

Added value: +{
+  "default": false,
+  "description": "Layer diff mode — compares each window against the buffered previous frame. First call = full I-frame (all windows). Subsequent calls = only changed windows (P-frame). Implicitly enables dotByDot. Best used with windowTitle=undefined to snapshot all windows.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Capture a specific monitor (0 = primary). Use get_screen_info to list displays.",
+  "minimum": 0,
+  "type": "integer"
+}

Added value: +{
+  "default": false,
+  "description": "1:1 pixel mode — no scaling, WebP compression. Window captures include 'origin: (x,y)' so you can compute screen position: screen_x = origin_x + image_x. When dotByDotMaxDimension is also set, scale factor is included: screen_x = origin_x + image_x / scale.",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Cap the longest edge (pixels) when dotByDot=true. Reduces payload while preserving coordinate math. Example: 1280 on a 1920×1080 screen → scale≈0.667. Response includes scale factor: screen_x = origin_x + image_x / scale. Recommended for Chrome: dotByDot=true, dotByDotMaxDimension=1280, grayscale=true.",
+  "type": "integer"
+}

Added value: +{
+  "default": false,
+  "description": "Convert to grayscale before encoding. Reduces file size ~50% for text-heavy content (e.g. AWS console, code editors). Avoid when color is meaningful (charts, status indicators).",
+  "type": "boolean"
+}

Added value: +{
+  "default": 768,
+  "description": "Max width or height in pixels (default 768). Use 1280 to read small text, code, or fine UI details. Ignored when dotByDot=true.",
+  "type": "integer"
+}

Added value: +{
+  "default": "auto",
+  "description": "OCR fallback behaviour when detail='text'. 'auto' (default): fire Windows OCR if UIA returns 0 actionable elements OR hints.uiaSparse=true (UIA returned <5 elements, typical for Chrome). 'always': always augment actionable[] with OCR words. 'never': disable OCR entirely.",
+  "enum": [
+    "auto",
+    "always",
+    "never"
+  ],
+  "type": "string"
+}

Added value: +{
+  "default": "ja",
+  "description": "BCP-47 language tag for the OCR engine (e.g. 'ja', 'en-US'). Only used when detail='text'.",
+  "type": "string"
+}

Added value: +{
+  "description": "Capture only this sub-region. Without windowTitle: virtual screen coordinates. With windowTitle: window-local coordinates — useful to exclude browser chrome (tabs/address bar). Example: windowTitle='Chrome', region={x:0, y:120, width:1920, height:900} skips the 120px browser chrome.",
+  "type": "object"
+}

Added value: +{
+  "default": 60,
+  "description": "WebP quality when dotByDot=true or diffMode=true. 40=layout only, 60=general (default), 80=fine text.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

Added value: +{
+  "description": "Capture only the window whose title contains this string. Prefer over full-screen when target window is known.",
+  "type": "string"
+}