browser_screenshotCapture PNG screenshots of a full page, the current viewport, or a specific element selected by CSS or XPath, so AI agents can visually verify page state and gather test evidence.
Capture a PNG screenshot of the whole page, viewport, or a selected element.
| Name | Required | Description | Default |
|---|---|---|---|
| fullPage | No | Capture the full page. Ignored when selector is provided. | |
| selector | No | Optional CSS or XPath selector for an element screenshot. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the output format (PNG) and the capture modes. However it never says what the tool actually returns (raw image content vs. a path/URL) or whether navigating first is a prerequisite, which are the details an agent most needs here.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler, and the resource plus scope options come first. It is efficient, though efficiency shades into under-specification here.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A simple two-parameter tool, but with no annotations and no output schema the description should still cover the return shape and any precondition such as an active page. It covers the what but not the how or the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the schema itself explains the fullPage/selector interaction, so the description adds no meaning beyond it. The phrase 'whole page, viewport, or a selected element' merely restates the parameter set; baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource (capture a PNG screenshot) and enumerates the three capture scopes that map to the parameters. It does not explicitly contrast with siblings browser_inspect or browser_interact, 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied by the tool's nature; there is no statement of when to prefer a screenshot over browser_inspect or browser_interact, and no note that the page must already be navigated to. An agent can infer the use case, but nothing is spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.