Agent Utility Suite (x402)

Read several web pages at once

scrape_batch

Read-onlyIdempotent

Use it when an agent needs to read several web pages at once: compare competitors' pricing pages, read the top search results, or the pages a site_map call found. Reads 2-5 public URLs in one paid call (one payment round trip instead of five), each exactly like scrape_markdown: the main content as clean Markdown (or mode: "full"), real tables, code blocks, metadata from meta tags and JSON-LD (author, dates, language, canonical URL), PDFs as text by page, RSS feeds as item lists, optionally each page's links. Results come back in request order, each either ok: true with the page or ok: false with an error code and message (bot check, unreachable, unsupported content), so one bad URL does not spoil the batch. Each page is cut at max_chars_per_page (default 20,000); next_calls continue a long page with scrape_markdown. If no page at all can be read, the call fails and is not charged. JavaScript is not executed. No account or API key. Costs $0.008 USDC per call via x402 ($0.002 per page when read one by one). Paid per call with x402 inside MCP (see the server instructions).

Input Schema

Name	Required	Description	Default
`via`	No	Optional: the tool whose next_calls suggested this call (filled in for you).
`mode`	No	main (default): each page's article or main content only. full: whole pages, including navigation and footers.	main
`urls`	Yes	2-5 different public http(s) URLs to read, e.g. ["https://example.com/pricing", "https://example.com/docs"]. Results come back in the same order.
`include_links`	No	Also return each page's links as a list (url, text, internal). Default false.
`strip_link_urls`	No	Write links as plain text in the Markdown (keeps the text, drops the URLs) to save tokens. Default false.
`max_chars_per_page`	No	Return at most this many characters of each page (1,000-50,000, default 20,000). Read the rest of a long page with scrape_markdown and its next_offset.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

addedInput schema / properties / via

Added value: +{
+  "description": "Optional: the tool whose next_calls suggested this call (filled in for you).",
+  "maxLength": 64,
+  "type": "string"
+}

AddedOct 6, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context beyond them: one payment round trip via x402, per-page ok:true/ok:false isolation so one bad URL does not spoil the batch, error codes (bot check, unreachable, unsupported content), JS not executed, no account/API key, and no charge if nothing can be read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The primary use case and batching benefit are front-loaded, and nearly every sentence carries information. It is a single dense block rather than a scannable structure, and the pricing clause ($0.008 vs $0.002 per page) takes some parsing, but there is little outright waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so fully: Markdown main content or full mode, tables, code blocks, meta/JSON-LD metadata, PDF and RSS handling, per-URL success/error shape and ordering. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the description still adds value by explaining the 2-5 URL constraint, request-order result mapping, the mode main/full distinction, and how max_chars_per_page truncation is resumed via scrape_markdown next_offset. It goes modestly beyond the schema without re-documenting every field.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('read several web pages at once', 'Reads 2-5 public URLs in one paid call') and explicitly positions itself against scrape_markdown ('each exactly like scrape_markdown') and site_map (as a URL source). An agent can tell it apart from the single-page sibling without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use triggers (compare competitors' pricing pages, read top search results, pages a site_map call found) and names scrape_markdown as the alternative for continuing a truncated long page. It stops short of an explicit 'use the single-page tool instead when you have only one URL' exclusion, so it is clear context rather than a full when/when-not/alternatives statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Agent Utility Suite (x402) tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?