Extract structured data as JSON from web pages by targeting JSON-LD, HTML tables, metadata, or CSS selectors; enable browser rendering for JavaScript-rendered sites.
Extract structured data (JSON-LD schema, HTML tables, metadata, and CSS-targeted nodes) as JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| use_browser | No | ||
| css_selector | No | ||
| extract_tables | No | ||
| extract_metadata | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden, and it discloses almost nothing beyond the output format ('as JSON'). It never explains that use_browser triggers headless rendering (with cost/latency implications), what happens on non-HTML or blocked pages, or any rate-limit/auth constraints.
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?
A single front-loaded sentence with the verb first and the extraction targets grouped in a parenthetical, so there is no wasted prose. The parenthetical is dense but each item earns its place by signalling a capability.
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?
For a five-parameter extraction tool with no annotations and zero schema descriptions, the description is thin: it does not cover the browser flag, defaults, or alternatives, and only the existence of an output schema spares it from explaining return values. An agent could invoke it, but not confidently choose the right mode.
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?
Schema description coverage is 0%, so the description must define the five parameters, but it only alludes to three of them through the parenthetical list (CSS-targeted nodes, tables, metadata). The most consequential flag, use_browser, is never mentioned, nor are the defaults (tables/metadata on by default, browser off by default), leaving behavior-changing toggles opaque.
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?
States a specific verb ('Extract') and resource ('structured data') and enumerates the concrete payloads it returns: JSON-LD schema, HTML tables, metadata, and CSS-targeted nodes. This is clearly distinguishable from siblings like extract_image_exif or extract_pdf, though the overlap with extract_schema is not addressed.
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?
The listed data types imply when to reach for this tool (structured markup rather than raw HTML), but there is no explicit when-to-use, when-not-to-use, or routing to scrape_url, scrape_dynamic, or extract_schema. The agent must infer the choice from the sibling list alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.