Skip to main content
Glama

Robot Actions — Remote Device Control

by com.robotactions.test
OverviewDiscussionsAdmin

Webpage hover

webpage_hover

Hover the pointer over an element in the device browser page, by CSS selector or by a ref from a page-elements listing (iOS Safari or Android Chrome, auto-detected). Scrolls it into view, waits for the scroll to settle, and dispatches a mouseMoved to its center — use it to reveal hover menus/tooltips before webpage_click. Returns x/y in VIEWPORT-relative CSS pixels, the same space webpage_click reports, never document-relative. On iOS the event is isTrusted:false. Throws if the target does not resolve.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
refNoElement ref from a page-elements listing, e.g. "e12". Provide this or `selector`. A ref points straight at the element it was issued for, so it survives markup that shifted position, and it can address elements no CSS selector can reach from the top of the page.
udidYesDevice UDID / serial (iOS or Android)
pageIdNoTarget page/tab id — auto-picked when omitted
socketNoAndroid only: abstract unix socket name (default: chrome_devtools_remote)
selectorNoCSS selector for the target element. Provide this or `ref`.
platformVersionNoIgnored (kept for compatibility)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / ref
      Added value: +{
+  "description": "Element ref from a page-elements listing, e.g. \"e12\". Provide this or `selector`. A ref points straight at the element it was issued for, so it survives markup that shifted position, and it can address elements no CSS selector can reach from the top of the page.",
+  "type": "string"
+}
    • changedInput schema / properties / selector / description
      Previous value: -"CSS selector for the element to hover"New value: +"CSS selector for the target element. Provide this or `ref`."
    • changedInput schema / required
      Previous value: -[
-  "udid",
-  "selector"
-]New value: +[
+  "udid"
+]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false) only sketch the profile, while the description discloses the real behavioral traits: it scrolls the target into view and waits for the scroll to settle (a side effect on page scroll position), dispatches a mouseMoved to the element center, returns viewport-relative x/y matching webpage_click's coordinate space, sets isTrusted:false on iOS, and throws when the target does not resolve.

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?

Front-loaded with verb+resource, then mechanics, then the usage cue and return contract; every sentence carries information. It is dense and slightly long for a single-action tool, but there is little waste.

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?

There is no output schema, and the description compensates by specifying the return values (x/y in viewport-relative CSS pixels, same space as webpage_click), plus failure behavior (throws if unresolved) and platform quirks. An agent has everything needed to call it and interpret the result.

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 100%, so the schema already documents `selector`, `ref`, `udid`, `pageId`, and `socket`. The description reinforces the selector-vs-ref duality and the coordinate space but adds no syntax or format detail beyond the schema, which is the baseline-3 case.

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?

Specific verb (hover) + resource (element in the device browser page) with the targeting modes named (CSS selector or page-elements `ref`) and platforms stated (iOS Safari / Android Chrome, auto-detected). It is clearly distinguishable from siblings like webpage_click and webpage_scroll_into_view, which it references by name.

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?

Explicitly says when to use it: 'use it to reveal hover menus/tooltips before webpage_click', which gives a concrete sequencing rule rather than leaving intent implicit. It does not state exclusions (e.g. when a plain click is preferable or that hovering is meaningless on touch-only targets), so it falls short of the top band.

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

All Robot Actions — Remote Device Control toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources