Capture high-quality screenshots of any webpage using headless browser. Price: $0.008
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to process | |
| width | No | Viewport width in pixels | |
| height | No | Viewport height in pixels | |
| timeout | No | Request timeout in milliseconds | |
| fullPage | No | Capture the whole scrollable page, not just the viewport | |
| selector | No | CSS selector to capture |
Changes observed during successful MCP inspections.
Input schema / properties / selector / examplePrevious value: -".main-content"New value: +"p"Input schema / properties / fullPage / defaultAdded value: +falseInput schema / properties / fullPage / descriptionPrevious value: -"Capture full page scroll"New value: +"Capture the whole scrollable page, not just the viewport"Input schema / properties / fullPage / exampleAdded value: +falseInput schema / properties / height / defaultAdded value: +720Input schema / properties / height / descriptionPrevious value: -"Viewport height (default 720)"New value: +"Viewport height in pixels"Input schema / properties / selectorAdded value: +{
+ "description": "CSS selector to capture",
+ "example": ".main-content",
+ "type": "string"
+}Input schema / properties / timeoutAdded value: +{
+ "default": 10000,
+ "description": "Request timeout in milliseconds",
+ "example": 10000,
+ "maximum": 30000,
+ "minimum": 5000,
+ "type": "number"
+}Input schema / properties / url / descriptionPrevious value: -"The URL to screenshot"New value: +"The URL to process"Input schema / properties / url / exampleAdded value: +"https://example.com"Input schema / properties / url / formatAdded value: +"uri"Input schema / properties / width / defaultAdded value: +1280Input schema / properties / width / descriptionPrevious value: -"Viewport width (default 1280)"New value: +"Viewport width in pixels"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the mechanism (headless browser) and the price ($0.008), which is valuable, but says nothing about the return format (image URL vs. binary), authentication, or failure behavior for a tool with six parameters.
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, front-loaded with the core action and ending with the pricing detail. Nothing redundant, though the pricing clause occupies the slot a usage hint would fill more usefully.
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?
Six parameters, no annotations, and no output schema. The description omits the most consequential unknown for a screenshot tool: what the caller actually receives (image URL, base64 payload, or file reference). For a tool with no output schema, that gap matters.
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 100%, so every parameter is already documented in the schema with types, bounds, and defaults. The description adds no syntax or interpretation beyond that, which is the expected baseline when the schema does the heavy lifting.
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 (capture screenshots) and resource (webpage), so the purpose is immediately clear. It does not, however, distinguish itself from siblings like fetch_webpage, preview_endpoint, or get_contents, which an agent must disambiguate before choosing.
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 gives no when-to-use guidance, no conditions, and no alternatives. An agent must infer that this is the tool for rendering a page visually rather than fetching its contents.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.