Capture a webpage or a specific element as a PNG screenshot. Use a CSS selector to target an element or enable full-page capture for the entire scrollable page.
Take a screenshot of the page or of a single element. Returns a PNG.
| Name | Required | Description | Default |
|---|---|---|---|
| selector | No | CSS selector of the element (optional, else the page) | |
| full_page | No | Capture the whole scrollable page |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the core behavior (screenshot of page/element) and the PNG output, but does not explain how the PNG is returned (e.g., base64, binary, path), behavior when an element is not found, or whether it waits for rendering to complete. This is a notable gap for an unannotated tool.
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 two short sentences with no filler. The primary action is front-loaded, and the PNG return type adds valuable information without redundancy. Every word earns its place.
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 two-parameter tool, the description covers the basic purpose and output, but lacks important context such as output encoding, error handling for invalid selectors, and interaction between full_page and selector. Given there is no output schema or annotations, these details would help an agent invoke and process the result 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?
Schema description coverage is 100%, so the schema already explains both parameters well. The description adds only the high-level notion of 'page or element', which mirrors the schema's selector description and does not provide additional detail about parameter interactions or edge cases.
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 a specific action ('Take a screenshot') and the resource ('page or of a single element'), distinguishing it from sibling browser tools that perform navigation, clicking, or evaluation. It also specifies the return format (PNG), making the tool's purpose unambiguous.
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?
The description makes it clear the tool is used for capturing either the whole page or a specific element, with the selector parameter determining which. There are no competing screenshot tools among the siblings, so no alternative routing is needed, but explicit when-to-use/when-not-to-use guidance is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.