Skip to main content
Glama

Screenshot the page

browser_screenshot
Read-only

Capture a PNG screenshot of the browser viewport or the full scrollable page for visual verification and debugging; use browser_snapshot to locate clickable elements.

Instructions

A PNG of the viewport, or the whole page with full_page. It carries no refs: use browser_snapshot to find things to click.

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": {
      "session_id": "<session_id>"
    },
    "name": "browser_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
timeoutNoSeconds; unset, 30.
full_pageNoCapture the whole scrollable page, not just the viewport.
session_idYesThe session_id `browser_open` returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.14.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint) and reach (openWorldHint), so the bar is lower. The description adds the genuinely important behavioral fact that the output is an image with no refs, which prevents the agent from trying to click on the result. It says nothing about where the image is delivered or size/timeout failure modes, keeping it short of a 5.

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 compact sentences with zero filler, and the key output fact (PNG, viewport vs full page) is front-loaded before the sibling redirect. Nothing could be removed without losing information.

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 no output schema, the description correctly carries the burden of saying what is returned — a PNG image — and how scope is controlled. Combined with full schema coverage and read-only annotations, an agent has enough to call it correctly. Only the delivery mechanism of the image is left implicit.

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 explains `full_page`, `timeout`, and `session_id`. The description's mention of `full_page` largely restates the schema's own wording ('Capture the whole scrollable page'). It adds no syntax, defaults, or constraints beyond what the structured field provides, so baseline 3 applies.

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?

The description names the concrete artifact ('A PNG of the viewport') and its scope variant ('the whole page with `full_page`'), so the agent knows exactly what it gets back. It also explicitly separates this tool from browser_snapshot by noting the result 'carries no refs.' It stops short of a clean verb+resource opening like 'Capture a screenshot,' but the purpose is unmistakable.

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?

It gives an explicit routing rule: use `browser_snapshot` to find things to click, implying this tool is for visual capture rather than element discovery. That is a real when-to-use signal tied to a named sibling. It doesn't state the converse case (when a screenshot is preferable to a snapshot beyond refs), so it's clear but not exhaustive.

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