screenshot_urlScreenshot a page → public image URL. $0.04/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Page URL. | |
| width | No | Viewport px. | |
| format | No | Default png. | png |
| height | No | Viewport px. | |
| quality | No | JPEG only, 1-100. | |
| fullPage | No | true = whole page, not viewport. |
Changes observed during successful MCP inspections.
Input schema / properties / format / descriptionAdded value: +"Default png."Input schema / properties / height / descriptionAdded value: +"Viewport px."Input schema / properties / quality / descriptionAdded value: +"JPEG only, 1-100."Input schema / properties / url / descriptionAdded value: +"Page URL."Input schema / properties / width / descriptionAdded value: +"Viewport px."Input schema / properties / fullPage / descriptionAdded value: +"true = whole page, not viewport."Input schema / properties / format / descriptionRemoved value: -"Image format: \"png\" (default) or \"jpeg\"."Input schema / properties / fullPage / descriptionRemoved value: -"Capture the entire scrollable page instead of just the viewport. Default false."Input schema / properties / height / descriptionRemoved value: -"Viewport height in pixels (default 800, 100–4000). Ignored when fullPage is true."Input schema / properties / quality / descriptionRemoved value: -"JPEG quality 1–100 (only applies when format is jpeg)."Input schema / properties / url / descriptionRemoved value: -"The URL of the page to screenshot (http:// or https://)."Input schema / properties / width / descriptionRemoved value: -"Viewport width in pixels (default 1280, 100–4000)."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing per-call cost ($0.04) and explicitly framing the 402 payment-required response as expected behavior rather than an error — a real trap for an agent. It stops short of describing rate limits, timeouts, or what the image URL looks like/expires.
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?
One compact line with the core action front-loaded, followed by cost and the non-failure 402 semantics in priority order. No wasted sentences.
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?
Covers the essentials an agent needs for a 6-param, no-output-schema tool: what comes back (a public image URL) and how billing/payment surfaces. Parameter details are fully handled by the schema, leaving only minor gaps like URL lifetime and error conditions other than 402.
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 width, height, format, quality, and fullPage are already documented with defaults and constraints. The description adds no parameter meaning beyond the schema, so the baseline 3 applies.
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?
"Screenshot a page → public image URL" names a specific verb, resource, and the shape of the output, which cleanly separates it from the fetch_* and conversion siblings. An agent knows exactly what it gets back without opening the schema.
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 clarifies the paid call model and what a 402 response means, which is genuinely useful usage context. It does not say when to prefer this over fetch_html or other rendering tools, so the alternative-selection guidance is only implied.
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.