agent-device

Official

Overview Schema Source Related Servers Discussions Admin

hover

Reveal hidden row toolbars and menus by moving the pointer over a UI target without pressing. Settle captures the revealed state for inspection.

Instructions

Move the pointer over a UI target by snapshot ref, selector, or coordinates without pressing, to reveal hover-gated UI such as row toolbars or menus. Web only; touch platforms have no hover state. Use settle to observe what the hover revealed without a follow-up snapshot. Times out after 90s; a caller-supplied budget extends it.

Input Schema

TableJSON Schema

Name	Required	Description
`raw`	No	Use raw snapshot data during selector resolution.
`udid`	No	Apple device or simulator UDID; the selector that pins one device when several share a name.
`debug`	No	Enable debug diagnostics.
`depth`	No	Snapshot traversal depth.
`runId`	No	Lease run identifier.
`scope`	No	Snapshot scope selector used before resolution.
`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`	Yes	UI target. This is separate from deviceTarget, which selects the device form.
`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).
`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

TableJSON Schema

Name	Required	Description
`x`	No	Resolved interaction x coordinate when available.
`y`	No	Resolved interaction y coordinate when available.
`ref`	No	Snapshot ref without the @ prefix when the target was an @ref.
`cost`	No
`hint`	No
`settle`	No
`gesture`	No
`message`	No
`warning`	No
`evidence`	No
`refLabel`	No
`selector`	No	Selector expression when the target was a selector.
`resolution`	No	Pre-action disclosure of how the acting path resolved its target. Absent when resolutionDisclosure is inapplicable for the path.
`targetKind`	Yes	Resolved interaction target kind.
`selectorChain`	No
`referenceWidth`	No	Reference frame width for visualizing the interaction point.
`targetHittable`	No
`referenceHeight`	No	Reference frame height for visualizing the interaction point.
`maestroFallbackReason`	No
`maestroNonHittableCoordinateFallbackUsed`	No	Whether the direct iOS Maestro coordinate fallback was actually used.
`maestroNonHittableCoordinateFallbackAllowed`	No	Whether the direct iOS Maestro coordinate fallback was allowed for this selector.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.21.2Sep 16, 2026

changedOutput schema / properties / evidence / properties / changedFromBefore / description

Previous value: -"Whether the post-action digest differs from the pre-action capture digest. false is evidence, not failure."New value: +"Whether the post-action digest differs from the pre-action capture digest. false is evidence, not failure. With surfaceChange present, no digest comparison is made: it reports that surface transition."

addedOutput schema / properties / evidence / 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"
+}

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"
-}

Addedv0.20.9Aug 19, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations present, the description carries a heavy burden and does a solid job: it discloses that the action does not press, that it is web-only, that it times out after 90 seconds, and that a caller-supplied budget can extend it. It also ties 'settle' to observing what hover revealed, adding behavioral context beyond the raw schema. It does not explain the response contents, but an output schema exists.

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

Conciseness5/5

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

Three sentences, each earning its place: action/purpose, platform restriction, and behavioral notes about settle and timeout. The most important information is front-loaded, and there is no filler or repetition.

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?

The schema is rich with 22 parameters and an output schema, so the description can focus on behavior, which it does. It covers core semantics, platform applicability, timeout, and the settle flow. The one gap is the ambiguous 'caller-supplied budget' – no parameter in the schema directly corresponds to it, which makes it unclear how an agent would extend the timeout.

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 coverage is 100%, so the baseline is 3. The description adds little beyond what the schema already documents: 'by snapshot ref, selector, or coordinates' mirrors the target oneOf, and the 'Use settle' note adds purpose to that parameter but no new syntax. The cryptic 'caller-supplied budget' is not mapped to a schema property, which slightly dilutes the value.

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?

The description opens with a specific verb and resource: 'Move the pointer over a UI target' and enumerates the three targeting modes: snapshot ref, selector, or coordinates. It explicitly says 'without pressing', which distinguishes it from sibling press/click/longpress tools, and it states the intended purpose: revealing hover-gated UI like row toolbars or menus.

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

Usage Guidelines4/5

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

The description gives clear context: use hover to reveal hover-gated UI, and gives an explicit when-not: 'Web only; touch platforms have no hover state.' It does not name an alternative tool like click or press, but 'without pressing' implies the boundary, so the guidance is clear though not exhaustive.

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

Deploy Server