Skip to main content
Glama

browser_screenshot

Capture a screenshot of any URL in Chrome to inspect rendered pages visually. Returns a PNG inline and saves a copy, with viewport or full-page options for OSINT verification.

Instructions

Open a URL in Chrome and return an actual screenshot image (PNG).

Set full_page=False for just the viewport. The image is returned inline so the model can look at the page; the file also stays in the shots directory.

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>"
    },
    "name": "browser_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
wait_msNo
full_pageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full burden, and it does disclose useful behavior: the result is an inline PNG the model can inspect, and a copy is persisted in the shots directory. It says nothing about navigation failures, timeouts, or what the implicit 1500ms wait actually waits for, which are the traits an agent needs to reason about reliability.

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?

Three short sentences, front-loaded with the purpose and output format, with no filler. Minor inefficiency: the full_page note is parameter guidance that arguably belongs in the schema rather than the prose.

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 a three-parameter tool with no annotations and no output schema, the description does well on the return value (inline PNG plus a file on disk). It is incomplete on the timing parameter and on failure/edge behavior, which matters for a browser-navigation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only explains one of three parameters: full_page, where 'Set full_page=False for just the viewport' usefully clarifies that the default means full-page capture. wait_ms is entirely unaddressed in both schema and description, leaving its timing semantics (units, what it waits for, before or after load) undefined.

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 action (open a URL in Chrome) and a specific, concrete return artifact (an actual screenshot image, PNG). Stating 'return an actual screenshot image' implicitly separates it from text-extraction or plain-open siblings like browser_extract and browser_open, so an agent can pick it 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 Guidelines3/5

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

Usage is only implied: an agent infers it should call this when it needs to visually inspect a page. There is no explicit statement of when this beats browser_extract or browser_open, and no exclusion or prerequisite guidance.

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