NythosX Agent Tools

read_url_as_markdown

Convert any web page into clean, readable Markdown. Fetches a public web page and returns clean Markdown: title, byline, site name, excerpt, word count and article body. Respects robots.txt, blocks private hosts, follows up to five redirects, caps the page at 3 MB. links=true adds outbound links. Not charged on failure: 403 if robots.txt disallows the path, 415 for non-HTML, 422 if no article text extracts, 502 on upstream error. Costs $0.003 USDC per call (x402).

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": "read_url_as_markdown"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Public http(s) URL to read
`links`	No	Include outbound links (max 200)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

No annotations exist, so the description carries the full burden and does so thoroughly: robots.txt compliance, private-host blocking, five-redirect cap, 3 MB page limit, HTTP status semantics (403/415/422/502) with the explicit note that failures are not charged, and the $0.003 USDC x402 cost. This is exactly the operational context an agent needs before calling an external fetch.

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

Conciseness5/5

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

Front-loads purpose in the first sentence, then packs return shape, safety limits, error codes, and pricing into a short block with no filler. Every clause conveys actionable information (a limit, an error meaning, or a cost).

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?

For a two-parameter fetch tool with no annotations and no output schema, the description supplies the return field list, fetch constraints, failure semantics, and pricing — everything needed to invoke it correctly and interpret a non-200 result. Nothing material is left unspecified.

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 the url and links parameters are already fully documented, including the max-200 link cap. The description's 'links=true adds outbound links' largely restates the schema. Baseline 3 applies since the schema does the heavy lifting and the description adds little new per-parameter meaning.

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 ('Convert any web page into clean, readable Markdown') and enumerates exactly what the return payload contains (title, byline, site name, excerpt, word count, article body). No sibling overlap exists (the other tools are gas-cost related), so no differentiation is needed and none is missing.

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?

Implicitly scopes usage by stating it 'Fetches a public web page' and 'Respects robots.txt, blocks private hosts,' which tells the agent the input class it accepts. It doesn't name a condition for choosing it over a hypothetical alternative or state what to do on non-article pages beyond the 422 error code, but with no competing sibling the guidance is sufficient.

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

All NythosX Agent Tools 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?