screenshot.com.ar

Take a screenshot of a web page

take_screenshot

Read-onlyIdempotent

Open a public web page in a real Chrome browser and return a screenshot image. Use it to see how a page looks: layout, design, visual bugs, charts, current visual state. To read the text of a page, prefer read_page.

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": {
      "url": "<url>"
    },
    "name": "take_screenshot"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Public http(s) URL of the page. If the scheme is missing, https:// is assumed.
`dark`	No	Ask the page for its dark color scheme (prefers-color-scheme: dark). Default false.
`width`	No	Viewport width in pixels (320-1920). Default 1280.
`format`	No	Image format. Default jpeg (smallest).
`height`	No	Viewport height in pixels (240-1920). Default 800.
`full_page`	No	Capture the whole scrollable page instead of only the viewport. Default false. Very long pages are cut at 8000 px.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the description doesn't need to restate safety. It adds real context beyond that: a live Chrome render, restriction to public pages, and that the result is an image rather than text. It leaves out load/wait behavior and any limits beyond the documented full_page cap.

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?

Two short sentences, front-loaded with the action and result, then the use case and the alternative. No wasted wording.

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?

With full schema coverage, annotations and no output schema, the description covers what to expect (an image, not text) and the public-page constraint. It omits how a partially loaded or JS-heavy page is handled, which would help an agent judge whether the screenshot is trustworthy.

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%, and every parameter (url, dark, width, height, format, full_page) is already documented with defaults and ranges in the schema. The description adds nothing about parameters, so the baseline 3 applies.

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 and resource ('open a public web page in a real Chrome browser and return a screenshot image') and immediately scopes it to visual inspection. It is clearly distinguishable from the sibling read_page, which it names.

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 enumerates when to use it (layout, design, visual bugs, charts, current visual state) and routes the text-reading case to read_page instead. That is a direct when/when-not/alternative statement.

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

All screenshot.com.ar tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?