Screenshot any public web page and return the image. 1 credit; cost in _meta.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL to capture. | |
| width | No | ||
| format | No | png | |
| height | No | ||
| receipt | No | Return a render receipt: image_sha256, extracted page text, viewport and timing, so you can trust the capture without inspecting pixels. | |
| full_page | No | Capture the whole scrollable page (default false = just the viewport). |
Changes observed during successful MCP inspections.
Input schema / properties / receiptAdded value: +{
+ "description": "Return a render receipt: image_sha256, extracted page text, viewport and timing, so you can trust the capture without inspecting pixels.",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the credit cost and the 'public web page' constraint. But it doesn't disclose error behavior, rate limits, or what happens for private/inaccessible pages, leaving significant behavioral gaps.
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 action, no 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?
The description covers the core function, cost, and public-page constraint. However, it doesn't mention the customizable parameters (width, height, format, full_page, receipt) or the return format details, though the schema fills some 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 description coverage is 50%, and the description does not add semantics for width, height, or format beyond the schema's enum/defaults. It only reiterates the 'public web page' aspect already in the url schema description.
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 uses a specific verb ('Screenshot') and resource ('any public web page'), clearly distinguishing it from sibling tools like generate_image (creates images) and list_templates (lists templates).
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?
It clearly states the tool captures any public web page, giving clear context for when to use it. However, it doesn't explicitly mention alternatives or when not to use it, such as for pages requiring authentication or for generating new images.
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.