smart-data-extractor

extract_from_url

Idempotent · 30s timeout · Extract structured data from URL content with auto schema learning. Pass idempotency_key to deduplicate identical calls within 5 minutes.

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>"
    },
    "name": "extract_from_url"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	HTTP(S) URL to fetch (will auto-download and parse), or raw content string (up to 200KB). Max 200KB after fetch.
`schema`	No	Optional pre-defined JSON Schema (draft-07). If omitted, schema is auto-inferred from content. Provide to enforce strict field extraction and type coercion.
`idempotency_key`	No	Optional UUID or unique identifier for 5-minute deduplication cache. Same key + tool = cached result in <5ms, zero re-fetching.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedMay 19, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / idempotency_key / description

Previous value: -"Optional client-supplied key for dedup within 5min cache"New value: +"Optional UUID or unique identifier for 5-minute deduplication cache. Same key + tool = cached result in <5ms, zero re-fetching."

changedInput schema / properties / schema / description

Previous value: -"Optional JSON Schema. If omitted, auto-inferred."New value: +"Optional pre-defined JSON Schema (draft-07). If omitted, schema is auto-inferred from content. Provide to enforce strict field extraction and type coercion."

changedInput schema / properties / url / description

Previous value: -"HTTP(S) URL to fetch, or raw content string"New value: +"HTTP(S) URL to fetch (will auto-download and parse), or raw content string (up to 200KB). Max 200KB after fetch."

addedInput schema / properties / url / examples

Added value: +[
+  "https://api.github.com/users/octocat",
+  "https://example.com/page.html",
+  "{\"name\":\"John Doe\",\"age\":30,\"email\":\"john@example.com\"}"
+]

First observedMay 17, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The description discloses idempotency, a 30s timeout, and a 5-minute deduplication cache, which are behavioral traits not covered by annotations (none provided). It does not discuss error handling, output format details, or authentication requirements, but the disclosed traits are valuable.

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?

The description is two sentences, starting with key traits (idempotent, timeout) and then the purpose. Every sentence adds distinct information; no filler.

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

Completeness3/5

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

The tool has 3 parameters, no output schema, and no annotations. The description covers the core extraction behavior and idempotency context, but does not explain the response format, how raw content strings are handled, or error conditions. This leaves the agent with some ambiguity about the tool's full behavior.

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?

All three parameters have schema descriptions with 100% coverage, so the description adds little beyond the schema. It reinforces that omitting 'schema' triggers auto-learning and that 'idempotency_key' enables deduplication, both already in schema descriptions.

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?

The description states 'Extract structured data from URL content with auto schema learning', which is a specific action on a specific resource. It distinguishes from batch_extract by focusing on a single URL, but does not explicitly name alternative tools. The raw content string option is not mentioned in the description, only in the schema.

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

Usage Guidelines3/5

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

The description provides conditional use of 'idempotency_key' to deduplicate calls, but does not explicitly state when to use this tool over sibling tools like auto_schema_learn, batch_extract, or extract_from_api. The 'auto schema learning' hint implies when to omit 'schema', but no direct alternatives are given.

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

All smart-data-extractor tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.