stealth_markdown_parserHardened headless-browser fetch with full JavaScript/SPA rendering and a realistic browser profile, returning fully rendered Markdown. Best for JavaScript-heavy/SPA pages and light bot checks; not guaranteed against advanced anti-bot walls (e.g. Cloudflare/Akamai). Price: $0.05 USDC per call.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Protected http(s) URL to fetch via stealth pipeline |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It reveals the use of a headless browser, realistic browser profile, full rendering, and return of Markdown. It also mentions pricing and limitations. However, it omits specifics like error handling, timeout behavior, or rate limits, which would make it more transparent.
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?
The description is a single, well-structured sentence that fronts the core action and purpose. It efficiently includes target use cases, limitations, and pricing without unnecessary words.
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?
Given the tool's simplicity (one parameter, no output schema, no annotations), the description provides all necessary context: what it does, when to use it, its limitations, and cost. It adequately answers the key questions an agent would have.
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 schema covers the single parameter 'url' with 100% description coverage, providing a clear definition ('Protected http(s) URL to fetch via stealth pipeline'). Baseline is 3; the tool description does not add additional parameter meaning beyond what the schema already provides.
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 clearly states the tool performs a hardened headless-browser fetch with JS/SPA rendering and returns Markdown. The title 'Stealth Anti-Bot' and the mention of 'light bot checks' distinguish it from the sibling surface_markdown_parser, which likely handles simpler pages.
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?
Explicitly states the tool is best for JavaScript-heavy/SPA pages and light bot checks, and explicitly warns it is not guaranteed against advanced anti-bot walls like Cloudflare/Akamai. This provides clear when-to-use and when-not-to-use 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.
Both tools parse web pages to Markdown, but they target different use cases: stealth handles JavaScript-heavy/SPA pages with a headless browser, while surface provides a basic fetch with noise stripping. Their distinct capabilities and price points make them easily distinguishable.
Both tool names follow a consistent pattern: an adjective (stealth_/surface_) followed by 'markdown_parser'. They share the same verb_noun structure and use underscores consistently.
With only two tools, the server feels minimal. While the two tools cover two main tiers of web parsing, the count is below the typical 3-15 range for a well-scoped server, but still reasonable for a focused purpose.
The tool set covers the primary use cases for converting web pages to Markdown: a basic mode for simple pages and a stealth mode for complex ones. Minor gaps exist, such as no batch processing or error handling tools, but the core functionality is well-covered.