Skip to main content
Glama

safari_native_click

Real click performed by WebKit through the macOS accessibility tree — mousedown/mouseup/click arrive with isTrusted: true, so WAF/bot-gated and isTrusted-checking handlers accept it (G2, Cloudflare, Google editors).

Instructions

Real click performed by WebKit through the macOS accessibility tree — mousedown/mouseup/click arrive with isTrusted: true, so WAF/bot-gated and isTrusted-checking handlers accept it (G2, Cloudflare, Google editors). Runs in the background: Safari is never activated, no window is raised and the mouse does not move. Use when regular safari_click has no effect or is rejected. Use ref (from snapshot), selector, text, or x/y. When using ref, always take a FRESH safari_snapshot first. Needs an unlocked screen.

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_click"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoViewport X coordinate
yNoViewport Y coordinate
refNoRef ID from safari_snapshot (e.g. '0_5')
textNoVisible text to find and click
receiptNoTab receipt from safari_new_tab — pins this call to that tab (survives reconnects/subagents)
selectorNoCSS selector
doubleClickNoDouble-click instead of single click

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. Addedv2.10.1
  9. Removedv2.3.1
  10. First observed

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: it discloses the event semantics (mousedown/mouseup/click with isTrusted:true), the background execution profile (Safari never activated, no window raised, mouse does not move), and the environmental prerequisite of an unlocked screen. These are exactly the non-obvious traits an agent cannot infer from the schema.

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-loads what the tool is and why it works, then the side-effect profile, then selection guidance and prerequisites. Dense but nearly every clause is load-bearing; the site-name list (G2, Cloudflare, Google editors) is slightly decorative but still aids selection.

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 a 7-parameter click tool with no annotations and no output schema, the definition covers mechanism, side effects, sibling choice, targeting options, and prerequisites. It stops short of stating failure behavior (what happens if no element matches) or what the call returns, which leaves a small gap.

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 coverage is 100%, so the baseline is 3; the description earns above that by explaining the targeting alternatives (ref, selector, text, or x/y) and by tying ref to a fresh safari_snapshot. It does not state precedence when multiple target params are supplied, which keeps it from a 5.

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+resource with a differentiating mechanism: a real WebKit click via the macOS accessibility tree producing isTrusted:true events. Explicitly contrasts with safari_click ("Use when regular safari_click has no effect or is rejected"), so the agent can pick between the two without opening the 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?

Gives the exact selection condition versus the sibling (when the regular click is ineffective or rejected) plus the target sites where it matters (G2, Cloudflare, Google editors). Also states a hard prerequisite ("Needs an unlocked screen") and a sequencing rule ("always take a FRESH safari_snapshot first" before using ref).

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