Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

extract

Turn a public URL into schema-conforming JSON matching a supplied bounded JSON Schema; parses pages as clean Markdown and notes when results are truncated.

Instructions

Extract schema-conforming JSON from a URL. Reads a public URL as clean Markdown, then returns data that strictly conforms to the supplied bounded JSON Schema. The response includes truncated, which is true when the page was too long and only its first part was used.

Input Schema

NameRequiredDescriptionDefault
extractOptionYesExtraction options

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.5
    • addedInput schema / properties / extractOption / properties
      Added value: +{
+  "instructions": {
+    "type": "string"
+  },
+  "render": {
+    "enum": [
+      "auto",
+      "http",
+      "browser"
+    ],
+    "type": "string"
+  },
+  "schema": {
+    "additionalProperties": {},
+    "type": "object"
+  },
+  "url": {
+    "type": "string"
+  }
+}
    • addedInput schema / properties / extractOption / required
      Added value: +[
+  "schema",
+  "url"
+]
  2. Addedv1.5.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose meaningful behavior beyond the schema: content is read as clean Markdown, output strictly conforms to the supplied schema, and the response carries a `truncated` flag when the page was too long. However, it says nothing about rate limits, failure modes on non-public/inaccessible URLs, or how the `render` enum (http vs browser) affects behavior.

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?

Three sentences, front-loaded with the core action and free of filler; the truncation note is the kind of detail that earns its place. Slightly more economical phrasing is possible but nothing is wasted.

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?

There is no output schema, so the description correctly explains the return: schema-conforming JSON plus a `truncated` indicator. That covers the essentials for a single-parameter extraction tool. It stops short of describing error behavior or whether truncation can break schema conformance, which a caller would reasonably want to know.

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 description coverage is 100% and the top-level parameter is documented as 'Extraction options', so the baseline is 3. The description adds one useful constraint not in the schema – the JSON Schema must be 'bounded' – but gives no added meaning for `render` or `instructions`, which the nested schema leaves undescribed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with unusual precision: 'Extract schema-conforming JSON from a URL', plus the mechanism ('reads a public URL as clean Markdown'). An agent immediately understands this is schema-driven structured extraction, not a generic scrape. It never names or contrasts with near siblings such as web_scrape or web_crawl, so differentiation is left to inference.

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

Usage Guidelines2/5

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

The phrase 'public URL' implies a precondition, but there is no explicit when-to-use statement, no when-not, and no routing to alternatives like web_scrape for raw content. With so many overlapping web tools in the sibling list, the absence of any comparative guidance is a real gap.

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

Deploy Server

Other Tools