Skip to main content
Glama

click

Activate a UI target by snapshot ref, selector, or coordinates, then confirm effects with settle or verify to ensure the app state changed as expected.

Instructions

Activate a UI target by snapshot ref, selector, or coordinates. Prefer a ref or selector after a snapshot; use coordinates only when semantic targeting is unavailable. This can change app state; use settle or verify to confirm the result without a follow-up snapshot.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory for command execution.
rawNoUse raw snapshot data during selector resolution.
udidNoiOS device UDID selector.
countNoNumber of press/click repetitions.
debugNoEnable debug diagnostics.
depthNoSnapshot traversal depth.
runIdNoLease run identifier.
scopeNoSnapshot scope selector used before resolution.
buttonNoPointer button for platforms that support mouse buttons.
deviceNoDevice name selector.
holdMsNoHold duration for each action.
serialNoAndroid device or Vega VVD serial selector.
settleNoAfter 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.
targetYesUI target. This is separate from deviceTarget, which selects the device form.
tenantNoRemote tenant identifier.
verifyNoCapture cheap post-action evidence (AX digest, node counts, changedFromBefore) instead of a follow-up snapshot.
leaseIdNoExisting lease identifier.
sessionNoAgent-device session name.
jitterPxNoRandomization radius in pixels.
noRecordNoDo not record this action.
platformNoPlatform selector used to resolve a device.
stateDirNoAgent-device state directory.
doubleTapNoRequest a double-tap action.
timeoutMsNoSettle: wait deadline in milliseconds (default 10000).
intervalMsNoDelay between repeated press/click actions.
includeCostNoInclude per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.
deviceTargetNoDevice target form. Maps to the CLI --target flag.
daemonBaseUrlNoRemote daemon base URL.
responseLevelNoResponse verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
settleQuietMsNoSettle: quiet window in milliseconds (default 500).
daemonAuthTokenNoRemote daemon auth token.
iosXctestEnvDirNoWritable directory for iOS XCTest runner env overlays.
mcpOutputFormatNoMCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.
iosXctestrunFileNoExternally built iOS XCTest runner .xctestrun artifact path.
iosSimulatorDeviceSetNoiOS simulator device-set path used for device resolution.
androidDeviceAllowlistNoAndroid serial allowlist used for device resolution.
iosXctestDerivedDataPathNoDerived data path for external iOS XCTest runner execution.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNoResolved interaction x coordinate when available.
yNoResolved interaction y coordinate when available.
refNoSnapshot ref without the @ prefix when the target was an @ref.
costNo
hintNo
countNoNumber of press/click repetitions.
buttonNo
holdMsNoHold duration for each action.
settleNo
messageNo
warningNo
evidenceNo
jitterPxNoRandomization radius in pixels.
refLabelNo
selectorNoSelector expression when the target was a selector.
doubleTapNoWhether the command requested a double-tap action.
intervalMsNoDelay between repeated press/click actions.
resolutionNoPre-action disclosure of how the acting path resolved its target. Absent when resolutionDisclosure is inapplicable for the path.
targetKindYesResolved interaction target kind.
selectorChainNo
referenceWidthNoReference frame width for visualizing the interaction point.
targetHittableNo
referenceHeightNoReference frame height for visualizing the interaction point.
maestroFallbackReasonNo
maestroNonHittableCoordinateFallbackUsedNoWhether the direct iOS Maestro coordinate fallback was actually used.
maestroNonHittableCoordinateFallbackAllowedNoWhether the direct iOS Maestro coordinate fallback was allowed for this selector.
Behavior3/5

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

No annotations are provided, so the description carries the full burden for safety. It discloses that the tool can change app state and recommends settle/verify for confirmation, but it does not address error behavior, permission requirements, or platform-specific side effects.

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 terse sentences front-load the core action and targeting preference, with no wordiness. Each sentence adds distinct information: what it does, when to use which targeting mode, and a safety tip.

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?

Given the tool's 37-parameter schema and presence of an output schema, the description covers the essentials: core action, targeting strategies, and a state-change warning. It omits edge-case behaviors like what happens when a target is not found, but the rich schema and output schema compensate for that.

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

Parameters4/5

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

With 100% schema description coverage, the baseline is 3, but the description adds meaningful guidance on selecting the target kind (ref/selector over coordinates), which enriches the semantics of the target parameter beyond the schema's own descriptions.

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 clearly states the action ('Activate a UI target') and the three targeting modes (ref, selector, coordinates). This distinguishes it from sibling tools like press or longpress by focusing specifically on click activation of UI elements.

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?

It provides explicit guidance: prefer ref/selector after a snapshot, use coordinates only when semantic targeting is unavailable, and use settle/verify to confirm state changes. However, it does not explicitly name alternative tools (e.g., press vs longpress), so it falls short of full when/when-not coverage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/callstack/agent-device'

If you have feedback or need assistance with the MCP directory API, please join our Discord server