Capture the browser viewport as a PNG; set full=true for the entire page, use clip coordinates for a region, or provide a path to write the file instead of returning it.
PNG of the viewport. full=true for the whole page, or clip={x,y,width,height}. path writes the file instead of returning it.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | tab id, defaults to current | |
| clip | No | ||
| full | No | ||
| path | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It does disclose two useful behavioral facts — the default scope is viewport-only unless full=true, and the image is returned inline unless path is given — but it omits what is actually returned when path is set (a path string? nothing?), and whether the capture waits for load or handles lazy content.
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 dense sentence with the output format front-loaded, followed by the two mode switches. There is no filler and every clause carries operative 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 simple read-only capture tool with no annotations and no output schema, the description covers the essential modes but leaves the return contract ambiguous when path is used, and says nothing about load timing or failure modes. Adequate but with visible gaps.
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 coverage is only 25%, so the description must compensate, and it mostly does: it explains full, the clip rectangle shape, and the path/return trade-off, none of which the schema documents. The only uncovered gap is that clip coordinates/pixel units and the tab parameter's default are left to the schema.
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?
The description states a specific resource and output format: a PNG image of the current viewport, with optional full-page or clipped variants. It is clear what the tool produces, but it never distinguishes itself from nearby siblings like snapshot, html, or text, which an agent could plausibly confuse with it.
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?
'full=true for the whole page, or clip={...}' gives parameter-level selection guidance, and 'path writes the file instead of returning it' explains the return-mode choice. However, there is no guidance on when to reach for screenshot versus snapshot/html/text, and no prerequisites or exclusions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.