Skip to main content
Glama
software-mansion

Argent

Official
by software-mansion
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

native-view-at-point

Identify the deepest visible UIView at a raw point to reveal what draws unlabeled icons, overlays, or custom cells. Returns class, identifier, frame, and ancestors when accessibility tree cannot name it.

Instructions

Inspect the deepest visible UIView at a raw native window point.

Unlike native-user-interactable-view-at-point, this ignores userInteractionEnabled, so it answers "what is visually here?" rather than "what would receive the touch?".

Use when a screenshot shows something the accessibility tree does not name — an unlabeled icon, a decorative overlay, a custom-drawn cell — and you need the class, identifier or nativeID of whatever draws it.

Returns { status: "ok", view }: the matched view with its class name, frames, identifier, label and layer name, its ancestor chain by default, and its subviews on request. view is null when nothing is drawn at that point.

IMPORTANT: x and y are raw points on the portrait axes of the screen, NOT normalized [0,1] simulator tap coordinates. To get them from a describe frame, multiply the normalized values by the screen size in points. Do this also when the UI is landscape.

If status is restart_required: follow the message (usually restart-app), then retry. If status is service_stale: the app is already injected, so restarting it cannot help — restart the tool-server (argent server stop && argent server start --detach) and retry. If the same status comes back after that restart, stop restarting: follow the message, which names the terminal fallback. If status is connect_pending: the app is injected and still connecting — do not restart it, wait a few seconds and retry. If status is init_failed: the simulator's native-devtools environment could not be initialised — follow the message (re-boot the simulator) rather than retrying this tool. A not-connected or not-running app comes back as one of those statuses rather than a failure. Failures are separate: an Apple system app is rejected outright (terminal — never retry it), and the point query itself can error or time out.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesRaw X coordinate in points, on the portrait axes of the screen (the axes of native-describe-screen frames). NOT normalized [0,1] tap space.
yYesRaw Y coordinate in points, on the portrait axes of the screen (the axes of native-describe-screen frames). NOT normalized [0,1] tap space.
udidYesSimulator UDID
fieldsNoView fields to include. Defaults: pointer, className, tag, frame, windowFrame, screenFrame, bounds, hidden, alpha, opaque, clipsToBounds, userInteractionEnabled, depth, identifier, label, layerName, nativeID. Additional: center, transform, contentMode, backgroundColor, tintColor
bundleIdYesBundle ID of the app
maxDepthNoMaximum depth for returned child/ancestor serialization (default 150)
skipClassesNoExact UIView class names whose entire subtree should be pruned
includeChildrenNoInclude child views for the matched view (default false)
includeAncestorsNoInclude ancestor chain for the matched view (default true)
skipClassPrefixesNoClass name prefixes to prune entire subtrees

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.26.0
    • changedInput schema / properties / fields / description
      Previous value: -"View fields to include. Defaults: pointer, className, tag, frame, windowFrame, bounds, hidden, alpha, opaque, clipsToBounds, userInteractionEnabled, depth, identifier, label, layerName, nativeID. Additional: center, transform, contentMode, backgroundColor, tintColor"New value: +"View fields to include. Defaults: pointer, className, tag, frame, windowFrame, screenFrame, bounds, hidden, alpha, opaque, clipsToBounds, userInteractionEnabled, depth, identifier, label, layerName, nativeID. Additional: center, transform, contentMode, backgroundColor, tintColor"
    • changedInput schema / properties / x / description
      Previous value: -"Raw X coordinate in the app window's native point space. NOT normalized [0,1] tap space."New value: +"Raw X coordinate in points, on the portrait axes of the screen (the axes of native-describe-screen frames). NOT normalized [0,1] tap space."
    • changedInput schema / properties / y / description
      Previous value: -"Raw Y coordinate in the app window's native point space. NOT normalized [0,1] tap space."New value: +"Raw Y coordinate in points, on the portrait axes of the screen (the axes of native-describe-screen frames). NOT normalized [0,1] tap space."
  2. First observedv0.15.0

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses the return shape (status, view), the null case, all non-ok statuses (restart_required, service_stale, connect_pending, init_failed) with explicit recovery actions, and separate failure modes (Apple system app rejection, point query errors/timeouts). This is far beyond typical tool descriptions.

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?

Long but every sentence earns its place. The opening line states purpose, the second differentiates from sibling, then usage, return format, coordinate conversion, and a systematic status/error walkthrough. It is well-structured with logical paragraph breaks and front-loads the most important information. No filler.

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

Completeness5/5

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

Given the absence of an output schema, the description fully compensates by explaining the return structure, status handling, and edge cases. It covers the coordinate system, default inclusion of ancestors, and the distinction between statuses and failures. For a 10-parameter tool, it is remarkably complete; the remaining parameters are self-explanatory from the schema.

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?

Schema description coverage is 100%, so baseline is 3. The description adds meaningful value beyond the schema by explaining the coordinate system conversion in detail and clarifying the default includeAncestors behavior. It does not re-explain every parameter, but the ones it addresses are the most error-prone. The added guidance pushes it to a 4.

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 ('Inspect') and resource ('deepest visible UIView') at a raw native window point, and explicitly contrasts with the sibling native-user-interactable-view-at-point by clarifying it ignores userInteractionEnabled. This gives an agent a crisp mental model of what the tool does and how it differs from the sibling without needing to open its schema.

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 states when to use it: when a screenshot shows something the accessibility tree does not name, and you need the class/identifier/nativeID. It also explains the coordinate conversion needed (raw points vs normalized tap space) and describes alternatives implicitly. No exclusions are missing; the 'use when' condition is direct and actionable.

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

Deploy Server

Other Tools