SiteCheck Web Intel

Extracts one article from a public news or blog page

search_article_extractor

Read-only

Extracts one article from a public news or blog page: headline (og:title or h1), author, published and modified times, description and the article body as Markdown. Reads the page you name only; paywalled text is not returned and body text depends on the page using or . Pages that refuse automated readers (BBC, AP News, Reuters and others) are read through a residential proxy and take a few seconds longer. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "search_article_extractor"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Full http or https address of an article page
`maxChars`	No	Longest body returned, 500 to 40000 characters (default 8000)

Output Schema

Name	Required	Description	Default
`url`	No
`body`	No
`author`	No
`source`	No
`headline`	No
`modified`	No
`bodyChars`	No
`checkedAt`	No
`published`	No
`truncated`	No
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses the meaningful behaviors: paywalled text is not returned, body extraction depends on <article>/<main> markup, some sites are read via residential proxy with added latency, and billing is $0.002 USDC per successful call with failures free. The per-call cost is exactly the kind of thing an agent needs before invoking.

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?

Front-loaded with purpose and output fields, then constraints, then pricing — a sensible order with no filler sentences. It is dense, packing scope, caveats and billing into a short block, which borders on cramped but every clause carries information.

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 an output schema present, the description needn't explain return structure, yet it still names the extracted fields while covering failure modes (paywall, unsupported markup, bot-blocked sites), latency, and cost model. Nothing an agent needs to decide whether to call it is missing.

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

Parameters3/5

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

Schema coverage is 100%, so url and maxChars (including the 500–40000 range) are already fully documented structurally; the description adds no new meaning about either parameter. Per the rubric, baseline 3 applies when the schema does the heavy lifting.

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 ('Extracts one article from a public news or blog page') and enumerates exactly what is returned (headline via og:title or h1, author, published/modified times, description, Markdown body). 'Reads the page you name only' distinguishes it from the many search_*_articles siblings, which locate articles rather than extract a named URL.

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?

The scope statement 'Reads the page you name only' plus the paywalled and <article>/<main> caveats tell the agent when this tool will and won't work. It stops short of explicitly routing the agent to the site-specific search tools (search_bbc_news_articles, search_reuters_articles) for URL discovery first, which is the one obvious missing hand-off.

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

All SiteCheck Web Intel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?