Skip to main content
Glama

Screenshot of a web page

screenshot_url

Take a picture of the web page at a public http(s) address: PNG, JPEG or WebP, the first screen or the whole page. The page is drawn by Chromium without running its own script (what the server sends is what is drawn), and only public addresses can be reached. scale 2 makes a sharper picture. Returns a download URL valid for one hour.

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": "screenshot_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPublic address of the page, starting with http:// or https://.
scaleNoPixels per CSS pixel. Default 1.
widthNoWindow width in CSS pixels. Default 1280.
formatNoDefault png.
heightNoWindow height in CSS pixels (the smallest height with full_page). Default 720.
qualityNoFor jpeg and webp. Default 85.
full_pageNoDraw the whole page, up to 16,000 pixels tall.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantive behavior beyond the annotations: no script execution (server-sent markup is what gets drawn), only public addresses are reachable, and the return value is a download URL expiring after one hour. The one-hour URL lifetime is critical operational context that neither the annotations nor the absent output schema provide.

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 dense sentences with no filler; the core action comes first, followed by rendering and reachability constraints, then the return-value caveat. Every clause carries information an agent needs.

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?

For a seven-parameter tool with no output schema, the description still covers the pieces that matter most: what gets rendered, network restrictions, and the nature and lifetime of the result. Remaining parameter details are fully handled by the schema.

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 url, scale, width, height, format, quality and full_page. The description only lightly reinforces this ('scale 2 makes a sharper picture', 'the first screen or the whole page'), adding little that the parameter descriptions do not already say.

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 concrete verb and resource ('Take a picture of the web page at a public http(s) address') plus the output formats and page scope. It also implicitly separates itself from create-a-file siblings like html_to_image by specifying that the page is fetched from a live URL and rendered by Chromium.

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 clear operating context: the address must be public http(s), and the rendering does not execute the page's own scripts. That tells the agent when the tool's output will be faithful and when it will not, though it never names a specific sibling to use instead (e.g. html_to_image for local markup).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources