Skip to main content
Glama

find

Locate UI elements on devices by text, label, value, role, or ID, then run actions like click, type, or wait.

Instructions

Find by text/label/value/role/id and run action

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory for command execution.
rawNo
lastNo
udidNoiOS device UDID selector.
debugNoEnable debug diagnostics.
depthNo
firstNo
queryYes
runIdNoLease run identifier.
valueNo
actionNo
deviceNoDevice name selector.
recordNoForce-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. On find, valid only for a read-only action.
serialNoAndroid device or Vega VVD serial selector.
targetNoAlias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element.
tenantNoRemote tenant identifier.
leaseIdNoExisting lease identifier.
locatorNo
sessionNoAgent-device session name.
noRecordNoDo not record this action.
platformNoPlatform selector used to resolve a device.
stateDirNoAgent-device state directory.
timeoutMsNo
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.
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 x coordinate for mutating find actions.
yNoResolved y coordinate for mutating find actions.
refNoSnapshot ref without the @ prefix when the find action returns one.
costNo
nodeNoSnapshot node for find get_attrs/get_text.
textNoText value returned by find get_text.
foundNoWhether a wait/exists/read-only find satisfied its condition.
queryNoQuery argument used for the find action.
settleNo
locatorNoLocator kind used for the find action.
matchesNoEvery match for the read-only find list action (#1625): { ref, node } each.
messageNoDiagnostic message for mutating find actions.
waitedMsNoMilliseconds waited for a read-only find condition.
refsGenerationNoADR 0014 ref frame epoch for read-only find actions.
Behavior2/5

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only states 'find' and 'run action', which omits critical details such as side effects of actions (e.g., clicking), error behavior when no element is found, or whether any state is modified. The description adds minimal behavioral context.

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 a single, efficient sentence that front-loads the core purpose. It is not redundant or bloated. However, the brevity sacrifices clarity on key aspects like the allowed actions, making it slightly less effective than it could be with a bit more structure.

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 highly complex tool with 34 parameters and no annotations, yet the description provides only a terse phrase. While an output schema exists (so return values are covered), the description still fails to convey the tool's overall workflow, device targeting nuances, or interaction with sibling tools. It is inadequate for the tool's complexity.

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?

The schema description coverage is 74%, which is moderate. The description adds useful meaning to the otherwise undocumented 'query' parameter by indicating it can be text, label, value, role, or id. However, it does not provide details for other undocumented parameters (e.g., depth, first, last). This partial compensation aligns with a baseline score of 3.

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 clearly states a verb ('Find') and the resource being searched (by text/label/value/role/id) and then says it runs an action. However, it does not specify what 'run action' entails or how it differentiates from sibling tools like click, get, or type. Thus it is clear but lacks sibling differentiation.

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

Usage Guidelines2/5

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

The description gives no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or recommended scenarios. The only implied usage is that you can locate by various attributes and then perform an action, but this is not explicit or elaborated.

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