Skip to main content
Glama

safari_native_hover

OS-level mouse hover via macOS CGEvent — moves the real cursor to an element to trigger native :hover / mouseenter handlers.

Instructions

OS-level mouse hover via macOS CGEvent — moves the real cursor to an element to trigger native :hover / mouseenter handlers. Use for obfuscated UIs where JS-dispatched mouseenter isn't enough, like Discord server sidebars (tooltips only appear on real hover) or portal-rendered tooltips. After hover, call safari_wait_for or safari_evaluate to read the tooltip. Dwells for dwellMs to let tooltips render, then restores the original cursor position by default. Requires Safari window to be visible.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "safari_native_hover"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoViewport X coordinate
yNoViewport Y coordinate
refNoRef ID from safari_snapshot
textNoVisible text to find and hover
dwellMsNoMilliseconds to dwell over the element so tooltips render (clamped 0-5000)
receiptNoTab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)
selectorNoCSS selector
restoreMouseNoRestore cursor to original position after dwell

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.24.1
    • addedInput schema / properties / receipt
      Added value: +{
      +  "description": "Tab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)",
      +  "type": "string"
      +}
  2. Addedv2.11.6
  3. Removedv2.11.3
  4. Addedv2.10.9
  5. Removedv2.10.8
  6. Addedv2.10.5
  7. Removedv2.10.4
  8. Addedv2.7.8
  9. Removedv2.4.0
  10. Addedv2.1.7

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses the real-cursor side effect, the dwell interval, the default cursor restoration, and the requirement that the Safari window be visible. It omits permission/accessibility requirements needed for CGEvent injection and what happens when the window is not visible.

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?

Front-loaded with the mechanism and purpose, then rationale, then follow-up, then side effects and prerequisite — every sentence adds information and none is filler.

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?

For an 8-parameter, unannotated interaction tool with no output schema, it covers purpose, side effects, prerequisites, and follow-up adequately. The notable gap is that with zero required parameters it never explains how x/y, ref, text, and selector interact or which takes precedence.

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 coverage is 100%, so each parameter is already documented, and the description mostly restates dwellMs and restoreMouse behavior rather than adding new meaning. It adds flow context (dwell so tooltips render, then restore) but no precedence between the x/y, ref, text, and selector targeting parameters.

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 mechanism and effect: 'OS-level mouse hover via macOS CGEvent — moves the real cursor to an element to trigger native :hover / mouseenter handlers.' The contrast with JS-dispatched mouseenter makes it distinguishable from the sibling hover tool without naming it.

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?

Gives concrete when-to-use conditions (obfuscated UIs, Discord sidebars, portal-rendered tooltips) and names follow-up calls (safari_wait_for or safari_evaluate) to read the tooltip. It does not explicitly say to prefer the plain safari_hover for ordinary cases or state when not to use this heavier OS-level path.

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