Skip to main content
Glama

Take a screenshot

browser_take_screenshot
Destructive

Take a screenshot of the current page. Use browser_snapshot for actions by default. With the vision capability enabled, use screenshot coordinates with the coordinate-based mouse tools for elements not exposed in the accessibility snapshot. Takes the session_id from open_browser. 0.1¢ a step that runs.

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>",
      "scale": "<scale>"
    },
    "name": "browser_take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoImage format for the screenshot. If unset, inferred from the filename extension, otherwise png.
scaleYesImage resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for the device pixel ratio). Default is css.css
targetNoExact target element reference from the page snapshot, or a unique element selector
elementNoHuman-readable element description used to obtain permission to interact with the element
filenameNoFile name to save the screenshot to. Relative file names are resolved against the workspace root. If not specified, the screenshot is saved into the output directory as `page-{timestamp}.{png|jpeg|webp}`.
fullPageNoWhen true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
session_idYesThe session id open_browser returned.

Output Schema

NameRequiredDescriptionDefault
urlNoThe address of the page after the step.
errorNoWhy the step failed, when it failed.
titleNoThe page title.
read_atNoWhen the page was read.
took_msNoHow long the step took.
price_usdNoWhat the step cost, in dollars.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "description": "The page after the step, and what the step cost.",
      +  "properties": {
      +    "error": {
      +      "description": "Why the step failed, when it failed.",
      +      "type": "object"
      +    },
      +    "price_usd": {
      +      "description": "What the step cost, in dollars.",
      +      "type": "number"
      +    },
      +    "read_at": {
      +      "description": "When the page was read.",
      +      "type": "string"
      +    },
      +    "title": {
      +      "description": "The page title.",
      +      "type": "string"
      +    },
      +    "took_ms": {
      +      "description": "How long the step took.",
      +      "type": "integer"
      +    },
      +    "url": {
      +      "description": "The address of the page after the step.",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description does not need to restate safety. It adds real value beyond them by disclosing the cost model ("0.1¢ a step that runs") and the session prerequisite (session_id comes from open_browser). It does not explain the destructiveHint=true in practice — i.e. that artifacts are written to the workspace/output directory — which is the one behavioral trait still missing.

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?

Four short sentences, front-loaded with the purpose and then the routing rule, with no filler. The cost and session notes earn their place, though the vision/coordinate sentence is slightly elliptical relative to the sibling tool names actually available.

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 an output schema present and full parameter coverage, the description only needs to cover selection and operational context, which it does: alternative tool, cost, session source. What remains thin is the explanation of why a screenshot tool carries destructiveHint=true, which an agent deciding whether to call it might want.

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 type, scale, target, element, filename and fullPage is already documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline score of 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?

The first sentence gives a specific verb and resource ("Take a screenshot of the current page") and the second immediately distinguishes it from the sibling browser_snapshot by role. An agent can tell what this tool does and what it is not for 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 Guidelines5/5

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

It names the alternative (browser_snapshot) and states the default preference for actions, then gives the explicit condition for selecting this tool instead (vision capability enabled, element absent from the accessibility snapshot, coordinate-based mouse tools). This is concrete when/when-not guidance rather than a vague hint.

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.