Skip to main content
Glama

Browser Screenshot

browser_screenshot

Captures full-page or targeted element screenshots to verify visual rendering and layout issues that an accessibility tree cannot diagnose, or to fulfill an explicit screenshot request.

Instructions

⚠️ WRONG TOOL — use browser_snapshot instead. browser_snapshot returns a compact text-based accessibility tree that is sufficient for 95% of use cases.

ONLY use browser_screenshot when:

  1. The user EXPLICITLY asks for a screenshot

  2. You need to verify visual rendering/layout issues that cannot be diagnosed from the accessibility tree

This tool returns a large image that rapidly fills up conversation context and degrades performance.

Args: full_page = capture entire scrollable page, selector = optional CSS selector to capture specific element.

Session parameter:

  • session=None (default): Uses primary session ("s1")

  • session="s2": Targets specific session (for parallel agents)

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "browser_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionNoSession ID (e.g., "s1", "s2"). None uses primary session.
agent_idNoAgent identifier for binding check. Optional.
selectorNoOptional CSS selector to capture specific element.
full_pageNoCapture entire scrollable page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose the key non-obvious trait: the tool returns a large image that rapidly consumes conversation context and degrades performance. It also explains session routing defaults. It does not say whether the image is returned inline or as a file reference, or whether a page must already be navigated, which keeps it from 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The warning and alternative are front-loaded, and the numbered conditions are easy to scan. The trailing 'Args:' sentence largely duplicates the fully-documented schema, so it is slightly less than zero-waste, but the rest is tight.

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?

There is no output schema, so the description must characterize the return value, and it does so by flagging the large image and its context cost. Prerequisites such as needing an active navigated page and the image delivery mechanism remain unstated, a minor gap for a 4-parameter, all-optional tool.

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 documents session, agent_id, selector, and full_page. The description restates full_page and selector and clarifies session default behavior, adding marginal meaning rather than new syntax or constraints. Baseline 3 is appropriate.

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 description names the specific resource (a screenshot image) and immediately distinguishes it from the sibling browser_snapshot, explaining that the sibling returns a compact accessibility tree. An agent can pick between the two without opening either 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 opens by declaring this the WRONG tool for most cases, then gives two explicit ONLY-use conditions (explicit user request; visual/layout verification not diagnosable from the accessibility tree) and points to the preferred alternative with a 95% heuristic. Both the when and the when-not are stated.

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