Capture the visible viewport as a PNG image. Crop to a region with coordinates and save the file to disk.
Screenshot the visible viewport as PNG. region [x0,y0,x1,y1] crops (zoom). savePath also writes the file.
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | Yes | Tab id from tabs_context | |
| region | No | ||
| savePath | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for behavioral disclosure. It mentions the side effect of savePath writing a file, which is useful, but it does not describe the return value (e.g., PNG data format) or whether the operation is non-destructive. It also lacks details on how region coordinates are interpreted (e.g., relative to viewport). This gap is significant for a tool with no annotation safety hints.
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?
The description is extremely concise: two sentences. The first front-loads the core purpose, and the second efficiently explains the two optional parameters. There is zero filler or redundant phrasing, making it highly scannable for an agent.
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 screenshot tool, the description covers the essential action, cropping, and file saving, but it omits critical context: the return format (e.g., does it return a base64 PNG?), coordinate system for region, and any caveats about scrolling or viewport boundaries. Since there is no output schema and no annotations, the description should be more thorough to fully equip the agent.
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?
The description adds meaning to region and savePath beyond the schema: it explains region as a crop box using [x0,y0,x1,y1] and savePath as an optional file write. However, it does not fully specify the coordinate system (e.g., pixels relative to viewport) or whether cropping implies scaling ('zoom' is ambiguous). With schema coverage at only 33%, the description partially compensates but leaves important details unclear.
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 clearly states it screenshots the visible viewport as PNG, specifying the verb (screenshot), resource (visible viewport), and output format. It distinguishes from read_page (which likely reads content) but does not explicitly name a sibling, so it's clear but not fully differentiated. It also mentions region cropping, adding scope specificity.
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?
No guidance is given on when to use this tool versus alternatives like read_page or resize_viewport. The description focuses on mechanics (region, savePath) but lacks context on when a screenshot is preferred over other observation tools. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.