Skip to main content
Glama

Click At

click_at

Perform pixel-based clicks at exact coordinates for captcha, canvas, or PDF elements when ARIA targeting fails. Use screenshot or inspect_element coordinates; prefer ARIA clicks when available.

Instructions

Pixel click for captcha/canvas/PDF where ARIA misses. Coords from screenshot/ inspect_element rect. Default to aria_click — pixel is fragile.

Ex: click_at('t0', 320, 480) → {"ok":true}

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tab_id": "<tab_id>",
      "x": "<x>",
      "y": "<y>"
    },
    "name": "click_at"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYes
yYes
buttonNoleft
tab_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden; it does add real value by flagging fragility and pushing the agent toward aria_click. However, it never says whether coordinates are viewport- or page-relative, whether the element is scrolled into view, or what a failure looks like beyond the happy-path {"ok":true}. Useful hints, but incomplete for a mutation tool with zero annotation coverage.

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?

Three short lines: purpose, coordinate source, fallback guidance, then a compact example. The most decision-relevant content (what it is and the aria_click default) is front-loaded with no filler.

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

Completeness3/5

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

Return shape is covered by the output schema and corroborated by the example, so that needn't be explained. But for a 4-parameter, 0%-coverage click primitive with no annotations, leaving the button parameter and the coordinate origin undocumented is a noticeable hole.

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 0%, so the description must compensate, and it partially does: the example fixes positional order (tab_id, x, y) and "Coords from screenshot/inspect_element rect" explains where x/y come from. The fourth parameter, button, is never mentioned, and the unit/origin of the coordinates is only implied.

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?

"Pixel click for captcha/canvas/PDF where ARIA misses" names a specific verb (click) and a specific mechanism (pixel coordinates) plus the exact scenarios it exists for. It also explicitly contrasts with aria_click, so the agent can pick between the two without inspecting either 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?

It gives both directions of routing: use this for captcha/canvas/PDF where ARIA fails, and "Default to aria_click — pixel is fragile." That is an explicit default plus the exclusion condition, which is exactly what the sibling set (aria_click, find_by_text, hover, drag) requires.

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