Capture a rendered image of any webpage for visual testing, debugging, or sharing. Set viewport size, format, and full-page capture.
Capture a rendered screenshot of any webpage. Cost: 1 credit.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to capture. | |
| width | No | Viewport width. | |
| format | No | Output format. | png |
| height | No | Viewport height. | |
| full_page | No | Capture full scrollable page. |
Changes observed during successful MCP inspections.
v0.3.1Input schema / properties / formatAdded value: +{
+ "default": "png",
+ "description": "Output format.",
+ "enum": [
+ "png",
+ "jpg",
+ "webp"
+ ],
+ "type": "string"
+}Input schema / properties / full_page / descriptionPrevious value: -"Capture full scrollable page"New value: +"Capture full scrollable page."Input schema / properties / heightAdded value: +{
+ "default": 720,
+ "description": "Viewport height.",
+ "type": "number"
+}Input schema / properties / url / descriptionPrevious value: -"URL to capture"New value: +"URL to capture."Input schema / properties / widthAdded value: +{
+ "default": 1280,
+ "description": "Viewport width.",
+ "type": "number"
+}v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose the credit cost, which is genuinely useful context an agent cannot get from structured fields, but it says nothing about rendering latency, timeouts, auth requirements, or what happens on unreachable URLs.
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 waste, action front-loaded and cost appended. Nothing redundant or padded.
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 five-parameter tool with no annotations and no output schema, the description is thin: it never says whether the result is image bytes, an inline image, or a URL, which matters given the absent output schema. The cost disclosure is the one piece of compensating detail.
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 all five parameters (url, width, height, format, full_page) are already documented with defaults and an enum in the schema. The description adds no parameter-level meaning, which is acceptable at this coverage level.
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: 'Capture a rendered screenshot of any webpage.' The word 'rendered' usefully distinguishes it from a raw HTML fetch, but the description never acknowledges the nearby sibling 'scrape', so an agent gets no explicit differentiation.
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 when-to-use guidance, no exclusions, no mention of alternatives such as scrape or site-intel. The only contextual note is the per-call cost, which is pricing, not usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.