SiteCheck Agent Intel & Dev

Converts raw HTML you send to GitHub-flavoured Markdown

agent_intel_html_dom_to_clean_markdown

Read-only

Converts raw HTML you send (up to 500 KB) to GitHub-flavoured Markdown: headings, paragraphs, links, images, lists, code blocks, quotes, bold and italic. Scripts, styles, navigation, footers, forms and comments are removed; tables are flattened to text. Relative links need a base URL to become absolute. Related tools on this server, for a different need: agent_intel_reader_markdown_extract when you need Reader view of one public https page: its . 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": {
      "html": "<html>"
    },
    "name": "agent_intel_html_dom_to_clean_markdown"
  }
}

Input Schema

Name	Required	Description	Default
`html`	Yes	HTML text, 1 to 500000 characters
`baseUrl`	No	Optional page address used to resolve relative links

Output Schema

Name	Required	Description	Default
`source`	No
`baseUrl`	No
`markdown`	No
`checkedAt`	No
`characters`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: names exactly what is stripped (scripts, styles, navigation, footers, forms, comments), warns that tables are flattened to text, notes the 500 KB input ceiling, and discloses the $0.002 x402 pricing model with the key detail that failed calls are not charged. The lossy-table behavior is the kind of surprise an agent must know before choosing this tool.

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 the core conversion contract, then the lossy behaviors, then the baseUrl caveat, then the alternative and price. Dense and largely waste-free, though the trailing price sentence reads as appended boilerplate rather than integrated context.

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

Completeness4/5

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

An output schema exists so return values need no explanation, and the description covers scope, limits, lossy transformations, link resolution and cost. The only real gap is error behavior beyond billing, which is minor for a stateless pure-function converter.

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 coverage is 100%, so the baseline is 3, but the description adds consequence beyond the schema: it explains why baseUrl matters ('Relative links need a base URL to become absolute'), which tells the agent the failure mode of omitting it. The 500 KB limit is repeated from the schema rather than added.

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 ('Converts raw HTML you send ... to GitHub-flavoured Markdown') and enumerates the output constructs produced. The 'raw HTML you send' framing immediately separates it from agent_intel_reader_markdown_extract, which fetches a page itself.

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?

Explicitly routes to the sibling for a different need ('agent_intel_reader_markdown_extract when you need Reader view of one public https page'), which implicitly tells the agent to use this tool when it already holds HTML. It stops short of an explicit when-not/exclusion statement for this tool itself, so it is clear context rather than a full decision rule.

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

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?