jevcrawl

scrape

Fetch a known web page and return its main text as ordered blocks; optionally filter blocks to a specific goal without following links.

Instructions

Fetch one known page and return its text as blocks, optionally pruned to a goal.

Without goal: every block of the page that survives the free filters (navigation, footers and repeated boilerplate removed), in page order, with no decision-model call. With goal: only the blocks that help answer it (blocks) plus borderline ones (uncertain); links are not followed.

Returns the same shape as crawl (blocks, uncertain, pages, stats), or {"error": code, "message": ...}. Text is verbatim with char_start/char_end offsets.

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": "scrape"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`goal`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 29, 2026

TDQS

A4.3/5.0

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 well: it discloses that free filters strip navigation/footers/boilerplate, that no decision-model call happens without a goal, that links are not followed, and the error envelope shape. It omits auth requirements, rate limits, and handling of JS-rendered or failed pages.

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?

Front-loaded with the core action, then a clean mode-by-mode breakdown, then return shape. Slightly wasteful in enumerating return keys (`blocks`, `uncertain`, `pages`, `stats`) that the existing output schema already documents.

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?

For a 2-parameter fetch tool with an output schema, this covers purpose, both modes, filtering behavior, and error shape — enough to invoke correctly. Remaining gaps are operational (timeouts, JS rendering, URL validation) rather than structural.

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, and it does for `goal` — explaining that it prunes output to relevant plus borderline (`uncertain`) blocks and avoids link following. `url` is only implied by 'one known page'; format or validation constraints (absolute URL, schemes) are never stated.

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?

States a specific verb and resource ('Fetch one known page and return its text as blocks') plus a scope qualifier ('links are not followed') that separates it from the crawl sibling. An agent can distinguish scrape from crawl/map without opening any schema.

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

Usage Guidelines4/5

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

Explicitly splits the two modes: 'Without `goal`: ...' versus 'With `goal`: only the blocks that help answer it', so the agent knows when the optional parameter changes behavior. It does not directly say when to prefer `crawl` or `map` instead, leaving that routing to inference from 'one known page'.

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

Deploy Server