Capture a screenshot of the current browser page, optionally including the full scrollable page, to visually verify or document web content.
Take a screenshot of the current page. Set full_page to capture the whole scrollable page.
| Name | Required | Description | Default |
|---|---|---|---|
| full_page | No | Whether to screenshot the full page (default: false) You should avoid fullscreen if it's not important, since the images can be quite large |
Changes observed during successful MCP inspections.
v3.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered and the description needn't restate it. The description adds no behavioral context beyond that: it does not say what is returned (inline image, base64, URL), whether it reflects only the viewport, or whether a session/navigation prerequisite applies. Adequate but thin for a tool with no output schema.
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?
Two short sentences, zero filler, with the core action front-loaded and the optional parameter note trailing. Nothing could be removed without losing information.
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?
For a one-optional-param, no-output-schema tool, the description covers the action and the only parameter, and annotations carry the safety profile. The main residual gap is the return format (image payload vs. reference) and the implicit requirement of an active browser session, though neither is needed to select the tool correctly.
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?
There is only one optional parameter and schema description coverage is 100% – the schema already explains full_page, its false default, and even warns about large images. The description's 'capture the whole scrollable page' adds a slight semantic clarification (whole scrollable page vs. viewport) but largely repeats structured data, so the 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: 'Take a screenshot of the current page.' That is unambiguous and distinguishable from data-extraction siblings like scraping_browser_get_html or scrape_as_markdown. It stops short of explicitly contrasting with scraping_browser_snapshot, which is the nearest ambiguous neighbor.
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 current page' – it presumes an active browsing session but never says so, and never says when a screenshot is preferable to snapshot, get_html, or get_text. The one piece of guidance present ('Set full_page to capture the whole scrollable page') is about the parameter, not about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.