Skip to main content
Glama

browser_screenshot

Capture a specified tab's viewport as a PNG while temporarily selecting it and restoring the prior tab without focusing the browser window.

Instructions

Capture the viewport as PNG. Temporarily selects the tab and restores the previous selection without focusing the window.

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

Input Schema

NameRequiredDescriptionDefault
tabIdYesTab id from browser_tabs.
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations provided, the description carries the burden, and it does disclose a meaningful side effect: the tab is temporarily selected, then the previous selection is restored without focusing the window. That is real behavioral value a schema cannot convey. However, it says nothing about permissions, failure modes when the tab is not visible/backgrounded, or what the call actually returns (image payload vs. file path), since there is no output schema to cover that.

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 tight sentences: the action and output format come first, then the side-effect caveat. Nothing is redundant and nothing important is buried.

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?

This is a low-complexity, two-parameter tool with fully documented schema, so little is required. The gap is that with no output schema and no annotations, the description never states what the caller receives back from a screenshot, which is the main remaining uncertainty for correct invocation.

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%, and both parameters (tabId, browser) are documented in the schema with sourcing hints, so the baseline of 3 applies. The description adds nothing about how these parameters affect behavior, and the word "viewport" only implicitly signals that there is no full-page option.

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?

"Capture the viewport as PNG" gives a specific verb, an explicit capture scope, and an output format, so the agent knows exactly what the tool produces. It does not distinguish itself from adjacent tools like browser_snapshot, browser_observe, or browser_accessibility, which likely also return page state in other forms.

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 is only implied: a PNG of the viewport suggests visual inspection where structured snapshots won't do, but the description never says when to prefer this over browser_snapshot or browser_accessibility, nor any exclusion. The agent must infer the routing decision from the word "PNG" alone.

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