Skip to main content
Glama

take_screenshot

Capture full-page or element-level screenshots of a webpage using your own Chrome or Edge via CDP, without Puppeteer or Playwright. Save pixel-perfect PNGs by URL, viewport, or CSS selector.

Instructions

Capture a pixel-perfect fullpage or element-level screenshot of a webpage using real Chrome/Edge CDP without Puppeteer/Playwright dependencies.

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>",
      "outputPath": "<outputPath>"
    },
    "name": "take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
dprNoDevice scale factor. Set to 2 for Retina/HiDPI display (default: 1)
urlYesTarget webpage URL (e.g. http://localhost:3000 or https://example.com)
delayNoAdditional delay in milliseconds after load to ensure animations/fonts finish (default: 1000)
widthNoViewport width in pixels (default: 1920)
heightNoViewport height in pixels (default: 1080)
waitForNoOptional CSS selector to wait for before taking screenshot
selectorNoOptional CSS selector to crop precisely to a specific DOM element (e.g. #header, .modal-card)
outputPathYesPath where the PNG screenshot should be saved (e.g. ./docs/screenshots/overview.png)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does add real context: it uses real Chrome/Edge via CDP and needs no Puppeteer/Playwright dependencies, which tells the agent about prerequisites. However, it omits key behavioral facts for a tool that writes to disk: whether an existing file at outputPath is overwritten, whether a browser must already be running, headless behavior, and what happens on navigation failure.

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?

A single front-loaded sentence with no filler; the mode distinction and the dependency-free implementation note are both packed in efficiently. 'Pixel-perfect' is mildly promotional but does not cost the reader anything.

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?

For an 8-parameter tool with no annotations and no output schema, the description covers purpose and implementation but not the file-write side effects, overwrite behavior, or what the call returns. An agent could invoke it, but would be guessing about side effects on outputPath.

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 every parameter including dpr, delay, waitFor, and selector is already documented in the schema; baseline 3 applies. The description only reinforces the fullpage-vs-element distinction that the selector parameter already conveys, adding no new syntax or format detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (capture) and resource (screenshot of a webpage) and distinguishes the two modes it supports: fullpage vs element-level. It does not name or differentiate itself from the siblings interact_and_screenshot or inspect_element, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

No explicit when-to-use or when-not-to-use guidance, and no mention of the sibling tools that also produce screenshots. The phrase 'fullpage or element-level' implies that supplying a selector switches modes, but the agent is left to infer that from the schema rather than the description.

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