jevcrawl

crawl

Finds answers across a website by searching toward a specific goal, returning only relevant passages verbatim with source URLs.

Instructions

Crawl a website toward a goal and return only the relevant passages, verbatim.

Use this instead of fetching pages yourself when the answer may be several pages deep (documentation, help centers, policies, product catalogs). A small decision model scores every block of text and every link, follows the most promising links first, and stops as soon as the collected text answers the goal. No language model runs inside the crawl.

Args: goal: A specific question to answer, e.g. "How many days do I have to get a refund?". Vague goals ("learn about the shop") return vague results. start_url: Where to start; the crawl stays on this host and its subdomains. max_pages: Page limit. Start with 10-30. max_seconds: Wall-clock limit. return_tokens: Most text (estimated tokens) to hand back. max_decision_usd: Hard limit on what the decision model may cost for this call.

Returns: blocks: relevant passages, best first. Each has url, heading_path, text (copied from the page), char_start/char_end (offsets into the page text whose sha256 is in pages) and relevance (0-1). uncertain: borderline passages. Read these before concluding something is missing. pages: every page fetched. stats: what it cost and why it stopped; check stats.stopped_because ("answered", "frontier_empty", "max_pages", "max_seconds", "budget") and stats.degraded (true means the decision model was unreachable and results are unscored). stats.needs_js_urls lists pages that only render with JavaScript and could not be rendered; stats.js_rendered_urls those it rendered. On failure: {"error": code, "message": ...}.

Quote returned text together with its url.

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": {
      "goal": "<goal>",
      "start_url": "<start_url>"
    },
    "name": "crawl"
  }
}

Input Schema

Name	Required	Description	Default
`goal`	Yes
`max_pages`	No
`start_url`	Yes
`max_seconds`	No
`return_tokens`	No
`max_decision_usd`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 29, 2026

TDQS

A4.5/5.0

Behavior5/5

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: it discloses the decision-model mechanism, that no language model runs inside the crawl, hard cost and time caps, the exact stopping reasons, the degraded mode when the scoring model is unreachable, and the JavaScript-rendering limitation. That is unusually complete for an unannotated tool.

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 purpose and the alternative-to-manual-fetching rationale, then organized into Args and Returns. The Returns section is long and partly overlaps the existing output schema, so some of it is less than fully earned, but the parts explaining stopped_because and degraded are genuine value.

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

Completeness5/5

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

For a six-parameter, cost-bearing crawl tool with no annotations, the description covers mechanism, limits, failure shape, and what to do with the output ('quote returned text together with its url'). An agent has everything needed to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 documents all six parameters with meaning the schema lacks — host/subdomain scoping for start_url, a suggested starting range for max_pages, and the cost-cap semantics of max_decision_usd. The goal parameter even gets a good/bad example pair.

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 (crawl a website) plus the distinctive output contract: only goal-relevant passages, returned verbatim. It implicitly separates itself from simple page fetching by scoping to answers that are 'several pages deep,' though it never names the scrape or map siblings explicitly.

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?

Gives a clear when-to-use rule ('use this instead of fetching pages yourself when the answer may be several pages deep') with concrete example domains, and adds operational guidance such as 'start with 10-30' pages and the warning that vague goals return vague results. No explicit when-not guidance relative to scrape or map, which keeps it short of a 5.

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

Deploy Server