APIVerve

Website Screenshot

WebsiteScreenshot

Read-only

Website Screenshot: Website Screenshot renders webpage screenshots from any URL as PNG, JPEG or WebP, with ads blocked and cookie notices dismissed. It returns a signed download link with an expiration timestamp, supporting custom viewport dimensions up to 3840 pixels wide, single-element capture by CSS selector, a capture delay, a page-load wait strategy and JPEG or WebP quality. (Cost: 40 credits)

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": "WebsiteScreenshot"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	The URL of the web page to capture the screenshot (e.g., https://example.com)
`type`	No	The image format for the screenshot	png
`delay`	No	Milliseconds to wait after the page loads before capturing, for animations or late content. Between 0 and 5000
`width`	No	The width of the screenshot in pixels (e.g., 1920). Must be between 100 and 3840	1920
`height`	No	The height of the screenshot in pixels (e.g., 1080). Must be between 100 and 3840	1080
`quality`	No	Compression quality from 1 to 100. Applies only when type is jpeg or webp
`fullpage`	No	Whether to capture the full page screenshot (true or false)
`selector`	No	CSS selector of a single element to capture instead of the viewport (e.g., #pricing). The first match is captured; a selector that matches nothing returns 400
`waituntil`	No	When navigation counts as finished before capture: domcontentloaded (default, fastest), load (all resources), or networkidle (network quiet). A page that never settles is captured as parsed	domcontentloaded

Output Schema

Name	Required	Description
`data`	No
`error`	No	Error message, null on success
`status`	No	"ok" on success

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds genuinely new behavioral facts: ads are blocked, cookie notices are dismissed, output is a signed download link with an expiration timestamp, and the call costs 40 credits. It also notes that a non-matching selector produces a 400, which is useful failure behavior.

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?

Two sentences, front-loaded with the verb and resource, then a dense but relevant feature/cost clause. Every item listed maps to a real capability, though the second sentence is long and slightly list-heavy.

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?

Given 9 parameters and an existing output schema, the description covers formats, size limits, capture modes, wait strategy, and even the delivery mechanism and cost. Minor gaps remain around when to prefer it over sibling conversion tools and any rate/permission constraints, but nothing needed to call it correctly is missing.

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 the schema already documents every parameter's meaning and constraints. The description mostly restates schema content (viewport width up to 3840, CSS-selector capture, delay, wait strategy, JPEG/WebP quality) without adding syntax or interaction rules beyond what the schema provides. 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+resource ('renders webpage screenshots from any URL') plus the output formats (PNG, JPEG, WebP), and the 'from any URL' framing implicitly separates it from HTML-source siblings like HTMLtoImage. An agent can identify the capability 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied by 'from any URL' and the feature list; there is no explicit statement of when to choose this over HTMLtoImage, WebsitetoPDF or WebsiteImagesScraper. No exclusions or prerequisites (e.g., JS-rendered pages vs static HTML) are given.

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

All APIVerve 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.