agent-device

Official

Overview Schema Source Related Servers Discussions Admin

snapshot

Capture the accessibility tree of a device or compare it against a previous baseline, with options for diffing and custom timeouts.

Instructions

Capture the accessibility tree or compare it with the previous session baseline. Use the returned refs for subsequent semantic interactions and the diff option to verify UI changes. Times out after 90s; a caller-supplied budget extends it.

Input Schema

TableJSON Schema

Name	Required	Description
`raw`	No
`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
`runId`	No	Lease run identifier.
`scope`	No
`device`	No	Device name selector (a UDID belongs in udid, a serial in serial).
`record`	No	Force-record this out-of-band observation into a repair-armed heal (mutually exclusive with noRecord). Authored replay steps are recorded automatically and never need this.
`serial`	No	Android, HarmonyOS, or Vega VVD serial selector.
`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.
`forceFull`	No
`timeoutMs`	No	Maximum wall-clock time for the snapshot command.
`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.
`customActions`	No	Name the affordances an element merged away (iOS UIAccessibilityCustomAction, React Native accessibilityActions) — a card whose reply/options controls are not separate elements still lists them here. The names are for PLANNING, not invocation: there is no API to trigger them, so reach the affordance through the element detail screen, through the same control exposed as a labeled element elsewhere, or by coordinates from its rect. iOS simulator only; costs one accessibility round trip per merged element.
`responseLevel`	No	Response verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
`interactiveOnly`	No
`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.

Schema Changelog

Changes observed during successful MCP inspections.

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"
+]

Changed1 schema field changedv0.20.6Aug 7, 2026

addedInput schema / properties / customActions

Added value: +{
+  "description": "Name the affordances an element merged away (iOS UIAccessibilityCustomAction, React Native accessibilityActions) — a card whose reply/options controls are not separate elements still lists them here. The names are for PLANNING, not invocation: there is no API to trigger them, so reach the affordance through the element detail screen, through the same control exposed as a labeled element elsewhere, or by coordinates from its rect. iOS simulator only; costs one accessibility round trip per merged element.",
+  "type": "boolean"
+}

Changed4 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"
+]

addedInput schema / properties / record

Added value: +{
+  "description": "Force-record this out-of-band observation into a repair-armed heal (mutually exclusive with noRecord). Authored replay steps are recorded automatically and never need this.",
+  "type": "boolean"
+}

changedInput schema / properties / serial / description

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

Changed3 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"
+}

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"
+]

Changed6 schema fields changedv0.17.6Jun 18, 2026

removedInput schema / properties / compact

Removed value: -{
-  "type": "boolean"
-}

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

A3.5/5.0

Behavior3/5

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

With no annotations, the description carries the behavioral disclosure burden. It usefully discloses the 90s timeout and that a caller-supplied budget extends it, and implies a read-only capture. However, it does not explain recording side effects given the record/noRecord parameters, how the session baseline is created, or what 'caller-supplied budget' maps to in the schema.

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?

The description is short, front-loaded with the primary action, and each sentence contributes useful information such as returned refs, diff usage, and timeout behavior. It loses a point because the 'or compare it with the previous session baseline' phrasing is dense and ambiguous rather than crisply structured.

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

Completeness2/5

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

This is a 24-parameter tool with no annotations and no output schema. The description covers the main purpose and timeout, but it does not explain the shape of the returned refs, what 'previous session baseline' means, or how the various selectors and recording options fit, leaving an agent without enough context to fully anticipate the response or side effects.

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 79%, so most parameters are already documented in the input schema. The description adds only general context about returned refs, diff usage, and timeout extension; it does not clarify the remaining undocumented parameters or explicitly connect 'caller-supplied budget' to timeoutMs, so its marginal semantic contribution is limited.

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

Purpose4/5

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

The description opens with a concrete verb and object: 'Capture the accessibility tree', and clarifies that the returned refs support subsequent semantic interactions. It is slightly ambiguous because 'or compare it with the previous session baseline' and 'the diff option' suggest snapshot itself may perform comparisons, while diff is a separate sibling tool.

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 practical guidance: use the returned refs for later semantic interactions and use the diff option to verify UI changes. This helps an agent choose snapshot as the prerequisite for semantic interaction and points to diff as the comparison alternative, though it does not explicitly say when not to use snapshot.

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

Deploy Server

snapshot

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools