Skip to main content
Glama
webscout-mcp

webscout-mcp

by wxs-lang

web_extract_schema

Extract structured web data by matching a JSON Schema—no CSS selectors or LLM key required—and return an object with per-field sources and explicit missing fields.

Instructions

Extract data matching a JSON Schema without writing selectors.

Pass the shape you want and get back an object; no CSS rules, no LLM key. Each field is resolved from the best available source, tried in this order:

  1. json-ld - the page's own structured data, so nothing is guessed

  2. meta - OpenGraph / Twitter cards

  3. semantic-html - h1, , itemprop, and a few class-name hints

The response records sources per field, so a caller can tell a stated value from an inferred one, and lists missing fields explicitly rather than leaving silent nulls.

Use web_extract instead when you already know the page's selectors: it is exact, whereas this infers. A field whose structure this has never seen comes back null - it will not invent a plausible value.

schema is JSON: {"type": "object", "properties": {"price": {"type": "number"}}}.

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>",
      "schema": "<schema>"
    },
    "name": "web_extract_schema"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
schemaYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.6.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the three-tier resolution order, that provenance is recorded per field via `sources`, that gaps surface as `missing` rather than nulls, and that unseen structures return null instead of a fabricated value. It omits operational traits such as auth requirements, rate limits, or whether multi-page crawling is supported, which keeps it from a 5.

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-loaded with a one-line statement of purpose, then a numbered resolution order that is genuinely informative, then the alternative-tool routing. The JSON snippet earns its place by resolving the string-vs-object ambiguity of `schema`.

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-shape detail is not required, yet the description still usefully flags `sources` and `missing` as interpretable outputs. Combined with the resolution order and degraded-case semantics, the definition is complete enough to call correctly; only the `url` parameter's behavior is underspecified.

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 0%, so the description must compensate. It explains `schema` thoroughly, including a concrete JSON example and the fact that it is passed as a JSON string, and clarifies that the returned object mirrors that shape. The `url` parameter gets no treatment at all — no indication of single-page scope, accepted formats, or behavior on redirects.

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?

Opens with a specific verb and resource plus the key differentiator ("without writing selectors"), and later names the sibling it replaces. An agent can tell it apart from web_extract purely from this text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use the alternative: "Use web_extract instead when you already know the page's selectors: it is exact, whereas this infers." It gives both the condition and the trade-off, leaving nothing to inference.

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