Screenshot 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. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the single destructiveHint annotation, the description discloses the $0.04/call cost and explains that a 402 with payment options is the expected, non-failure response for unpaid calls. This adds valuable behavior context not present in annotations.
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 compact sentences deliver the core purpose and output first, followed by a necessary payment caveat. Every word adds value with no redundancy.
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?
With no output schema, the description still states the return type ('public image URL') and explains the important payment behavior. This is sufficient for an agent to understand the tool's operation and expected results.
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?
The input schema has 100% coverage with descriptions for all 6 parameters, so the description need not repeat them. It adds no additional parameter-specific meaning, matching the baseline for full schema coverage.
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') with a clear resource ('a page') and states the output ('public image URL'). This clearly distinguishes it from sibling tools like fetch_html or fetch_metadata, which return text/data rather than images.
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?
Usage is implied by 'Screenshot a page', but there is no explicit guidance about when to choose this over alternatives or any exclusions. The payment note is operational context, not tool-selection guidance.
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.
Several tools overlap in fetching and processing web content (fetch_extract, fetch_html, fetch_metadata, html_to_markdown), which could confuse an agent. However, descriptions clarify output types, so most tools are distinguishable.
Names follow mixed conventions: verb_noun (fetch_html, remove_background), noun_verb (csv_query, rss_parse), and noun_noun (tool_catalog, screenshot_url). Each name is descriptive, but the lack of a consistent pattern makes it harder to guess tool names.
With 17 tools, the count is slightly above the ideal 3-15 range but still manageable. The inclusion of 5 meta-tools (pricing, tool_catalog, task_recipes, memory_snippet, use_tool) inflates the count but serves a discovery purpose.
The toolkit covers a broad range of web and data tasks (fetch, parse, query, convert, image, SEO). Minor gaps exist (e.g., no OCR, no image editing), but use_tool can dynamically access additional tools, mitigating incompleteness.
