agent-device

Official

Overview Schema Source Related Servers Discussions Admin

back

Return to the previous screen in an app or via system navigation. Choose in-app for the app's navigation stack or system for platform behavior.

Instructions

Navigate back in the app or through system navigation. Use in-app for the app navigation stack and system when the platform back behavior is required. On iOS, a single-screen iPhone or an iPad whose app provably fills its screen can use a top-leading tap when the app tree is unreadable, with before/after visual verification. A capture failure reports an unknown outcome. Times out after 90s; a caller-supplied budget extends it.

Input Schema

Name	Required	Description
`mode`	No
`udid`	No	Apple device or simulator UDID; the selector that pins one device when several share a name.
`debug`	No	Enable debug diagnostics.
`runId`	No	Lease run identifier.
`device`	No	Device name selector (a UDID belongs in udid, a serial in serial).
`serial`	No	Android, HarmonyOS, or Vega VVD serial selector.
`settle`	No	After the action, wait for the UI to go quiet and return the settled diff vs the pre-action tree in the same response. Best-effort; never fails the action.
`target`	No	Alias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element.
`tenant`	No	Remote tenant identifier.
`leaseId`	No	Existing lease identifier.
`session`	No	Agent-device session name.
`noRecord`	No	Do not record this action.
`platform`	No	Platform selector used to resolve a device.
`timeoutMs`	No	Settle: wait deadline in milliseconds (default 10000).
`includeCost`	No	Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.
`deviceTarget`	No	Device target form. Maps to the CLI --target flag.
`responseLevel`	No	Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
`settleQuietMs`	No	Settle: quiet window in milliseconds (default 500; 300 when the settled tree comes from the iOS simulator snapshot bridge). On iOS, a broad screen replacement such as a modal dismissal is confirmed for at least 1500ms whatever window is asked for, within the timeoutMs settle deadline; a replacement from a screen the pre-action capture read as presenting nothing, such as a tab switch, gets no 1500ms confirmation and keeps the asked window.
`mcpOutputFormat`	No	MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.
`androidDeviceAllowlist`	No	Android serial allowlist used for device resolution.

Output Schema

Name	Required	Description	Default
`mode`	Yes
`action`	Yes
`settle`	No
`message`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.21.28Oct 15, 2026

changedInput schema / properties / settleQuietMs / description

Previous value: -"Settle: quiet window in milliseconds (default 500)."New value: +"Settle: quiet window in milliseconds (default 500; 300 when the settled tree comes from the iOS simulator snapshot bridge). On iOS, a broad screen replacement such as a modal dismissal is confirmed for at least 1500ms whatever window is asked for, within the timeoutMs settle deadline; a replacement from a screen the pre-action capture read as presenting nothing, such as a tab switch, gets no 1500ms confirmation and keeps the asked window."

Changed1 schema field changedv0.21.2Sep 16, 2026

addedOutput schema / properties / settle / properties / surfaceChange

Added value: +{
+  "description": "Present when an in-place system surface (web sign-in or Apple Pay sheet) was presented over the app, or left it.",
+  "properties": {
+    "disclosure": {
+      "description": "Agent-facing sentence explaining the surface transition.",
+      "type": "string"
+    },
+    "from": {
+      "description": "Surface the pre-action baseline described: a host bundle id, or app.",
+      "type": "string"
+    },
+    "to": {
+      "description": "Surface the post-action capture describes: a host bundle id, or app.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "from",
+    "to",
+    "disclosure"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedv0.21.0Sep 9, 2026

changedInput schema / properties / device / description

Previous value: -"Device name selector."New value: +"Device name selector (a UDID belongs in udid, a serial in serial)."

changedInput schema / properties / serial / description

Previous value: -"Android device or Vega VVD serial selector."New value: +"Android, HarmonyOS, or Vega VVD serial selector."

changedInput schema / properties / udid / description

Previous value: -"iOS device UDID selector."New value: +"Apple device or simulator UDID; the selector that pins one device when several share a name."

Changed8 schema fields changedv0.20.10Aug 26, 2026

removedInput schema / properties / cwd

Removed value: -{
-  "description": "Working directory for command execution.",
-  "type": "string"
-}

removedInput schema / properties / daemonAuthToken

Removed value: -{
-  "description": "Remote daemon auth token.",
-  "type": "string"
-}

removedInput schema / properties / daemonBaseUrl

Removed value: -{
-  "description": "Remote daemon base URL.",
-  "type": "string"
-}

removedInput schema / properties / iosSimulatorDeviceSet

Removed value: -{
-  "description": "iOS simulator device-set path used for device resolution.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestDerivedDataPath

Removed value: -{
-  "description": "Derived data path for external iOS XCTest runner execution.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestEnvDir

Removed value: -{
-  "description": "Writable directory for iOS XCTest runner env overlays.",
-  "type": "string"
-}

removedInput schema / properties / iosXctestrunFile

Removed value: -{
-  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
-  "type": "string"
-}

removedInput schema / properties / stateDir

Removed value: -{
-  "description": "Agent-device state directory.",
-  "type": "string"
-}

Changed1 schema field changedv0.20.9Aug 19, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "apple",
-  "android",
-  "vega",
-  "linux",
-  "web",
-  "ios",
-  "macos"
-]New value: +[
+  "apple",
+  "android",
+  "harmonyos",
+  "vega",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

Changed4 schema fields changedv0.20.6Aug 7, 2026

addedInput schema / properties / settle

Added value: +{
+  "description": "After the action, wait for the UI to go quiet and return the settled diff vs the pre-action tree in the same response. Best-effort; never fails the action.",
+  "type": "boolean"
+}

addedInput schema / properties / settleQuietMs

Added value: +{
+  "description": "Settle: quiet window in milliseconds (default 500).",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / timeoutMs

Added value: +{
+  "description": "Settle: wait deadline in milliseconds (default 10000).",
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / settle

Added value: +{
+  "properties": {
+    "captures": {
+      "type": "number"
+    },
+    "diff": {
+      "description": "Settled diff vs the pre-action tree (changed lines only).",
+      "properties": {
+        "lines": {
+          "items": {
+            "properties": {
+              "kind": {
+                "enum": [
+                  "added",
+                  "removed"
+                ],
+                "type": "string"
+              },
+              "ref": {
+                "description": "Plain ref body (e12) for added lines.",
+                "type": "string"
+              },
+              "text": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "kind",
+              "text"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "summary": {
+          "properties": {
+            "additions": {
+              "type": "number"
+            },
+            "removals": {
+              "type": "number"
+            },
+            "unchanged": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "additions",
+            "removals",
+            "unchanged"
+          ],
+          "type": "object"
+        },
+        "truncated": {
+          "description": "Lines were capped to the response bound.",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "summary",
+        "lines"
+      ],
+      "type": "object"
+    },
+    "hint": {
+      "type": "string"
+    },
+    "quietMs": {
+      "type": "number"
+    },
+    "refs": {
+      "items": {
+        "properties": {
+          "ref": {
+            "description": "Plain ref body (e12) minted from the stored settled tree.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "ref"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "refsGeneration": {
+      "description": "Snapshot generation of the stored settled tree; refs on added diff lines were minted from it.",
+      "type": "number"
+    },
+    "settled": {
+      "description": "Whether the UI held the quiet window before the deadline. false is advisory, not failure.",
+      "type": "boolean"
+    },
+    "tail": {
+      "description": "Unchanged interactive refs tail: still-present, actionable elements from the settled tree, attached only when diff carries zero added-line refs (a modal-dismiss/toast-only diff).",
+      "items": {
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "ref": {
+            "description": "Plain ref body (e12) minted from the stored settled tree.",
+            "type": "string"
+          },
+          "role": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "ref",
+          "role"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "tailTruncated": {
+      "description": "Present (true) when tail candidates exceeded the response cap.",
+      "type": "boolean"
+    },
+    "timeoutMs": {
+      "type": "number"
+    },
+    "waitedMs": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "settled",
+    "waitedMs",
+    "captures",
+    "quietMs",
+    "timeoutMs"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedv0.20.2Jul 30, 2026

addedInput schema / properties / noRecord

Added value: +{
+  "description": "Do not record this action.",
+  "type": "boolean"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "apple",
-  "android",
-  "linux",
-  "web",
-  "ios",
-  "macos"
-]New value: +[
+  "apple",
+  "android",
+  "vega",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

changedInput schema / properties / serial / description

Previous value: -"Android serial selector."New value: +"Android device or Vega VVD serial selector."

Changed4 schema fields changedv0.17.11Jul 6, 2026

addedInput schema / properties / includeCost

Added value: +{
+  "description": "Include per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.",
+  "type": "boolean"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "macos",
-  "android",
-  "linux",
-  "web",
-  "apple"
-]New value: +[
+  "apple",
+  "android",
+  "linux",
+  "web",
+  "ios",
+  "macos"
+]

addedInput schema / properties / responseLevel

Added value: +{
+  "description": "Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.",
+  "enum": [
+    "digest",
+    "default",
+    "full"
+  ],
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "action": {
+      "const": "back",
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "mode": {
+      "enum": [
+        "in-app",
+        "system"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "action",
+    "mode",
+    "message"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.17.7Jun 23, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "macos",
-  "android",
-  "linux",
-  "apple"
-]New value: +[
+  "ios",
+  "macos",
+  "android",
+  "linux",
+  "web",
+  "apple"
+]

Changed5 schema fields changedv0.17.6Jun 18, 2026

addedInput schema / properties / iosXctestDerivedDataPath

Added value: +{
+  "description": "Derived data path for external iOS XCTest runner execution.",
+  "type": "string"
+}

addedInput schema / properties / iosXctestEnvDir

Added value: +{
+  "description": "Writable directory for iOS XCTest runner env overlays.",
+  "type": "string"
+}

addedInput schema / properties / iosXctestrunFile

Added value: +{
+  "description": "Externally built iOS XCTest runner .xctestrun artifact path.",
+  "type": "string"
+}

addedInput schema / properties / mcpOutputFormat

Added value: +{
+  "description": "MCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.",
+  "enum": [
+    "optimized",
+    "json"
+  ],
+  "type": "string"
+}

changedInput schema / properties / platform / enum

Previous value: -[
-  "ios",
-  "android",
-  "macos",
-  "linux",
-  "apple"
-]New value: +[
+  "ios",
+  "macos",
+  "android",
+  "linux",
+  "apple"
+]

First observedv0.16.9Jun 3, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses the 90s timeout, caller-supplied budget extension, that a capture failure reports an unknown outcome, and the before/after visual verification for the fallback. It leaves the softer behaviors (settle, noRecord, includeCost) to the schema, so not a full 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Core behavior is front-loaded and each sentence carries distinct information, but the iOS fallback sentence is dense and would benefit from slightly tighter phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a heavily parameterized tool with an output schema and no annotations, the description covers the key runtime behavior, timeout, and fallback conditions. Device/session plumbing is left to the schema, which is reasonable given 95% coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 95%, so the schema already documents all 20 params thoroughly. The description adds meaning for the mode enum but does not elaborate on the many device/session/response options, landing at baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and navigation scope, then immediately distinguishes the two modes (in-app navigation stack vs system back), which makes it clear how this differs from siblings like home or app-switcher.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use each mode ('Use in-app for the app navigation stack and system when the platform back behavior is required') and gives a precise condition for the iOS top-leading-tap fallback.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

back

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools