OpenChrome

crawl_start

Initialize a resumable web crawl job without network I/O, returning a job ID for later step-by-step progress tracking.

Instructions

Initialise a resumable crawl job. Returns { jobId, status: "pending" } immediately — performs NO network I/O. Drive progress with crawl_status({ jobId, advance: N }) which fetches up to N pages per call. Same args as the legacy crawl tool. Use crawl_cancel to stop.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	REQUIRED Starting URL to crawl
`scope`	No	URL glob limiting which URLs to follow. Default: same origin.
`delay_ms`	No	Delay between page fetches (ms). Default: 1000
`max_depth`	No	Max link-follow depth. Default: 2
`max_pages`	No	Max pages to crawl. Default: 20
`cache_mode`	No	Opt-in crawl content cache mode. Default: disabled.
`cache_scope`	No	Cache namespace/safety scope. Default: public.
`concurrency`	No	Max parallel fetches. Default: 3
`cache_ttl_ms`	No	Maximum age for enabled/read_only cache hits. Omit for no TTL expiry.
`includeLinks`	No	For markdown-clean, include link destinations in markdown. Default: true
`output_format`	No	Content format. Default: markdown
`respect_robots`	No	Whether to obey robots.txt. Default: true
`onlyMainContent`	No	For markdown-clean, remove nav/footer/ads before conversion. Default: true
`exclude_patterns`	No	URL globs — skip links matching any.
`include_patterns`	No	URL globs — follow only links matching at least one.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.12.8Jun 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Discloses that the tool returns immediately with a pending status and does no network I/O. Annotations are sparse (no readOnly/destructive/idempotent hints), so description carries the full burden and does so effectively.

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?

Three concise sentences with no wasted words. Purpose is front-loaded, followed by behavioral note and usage instructions.

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?

Despite 15 parameters and no output schema, the description clearly explains the return format and the follow-up steps (crawl_status, crawl_cancel). The workflow is fully contextualized.

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%, so the description adds little beyond 'Same args as the legacy crawl tool'. This reference to a known sibling is helpful but does not increase semantic value beyond the schema defaults.

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?

Clearly states it initializes a resumable crawl job, returns a jobId immediately, and performs no network I/O. Distinguishes from siblings by specifying that progress is driven via crawl_status and stopping via crawl_cancel.

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 instructs to use crawl_status for progress and crawl_cancel for stopping. Also mentions it has the same arguments as the legacy crawl tool, providing clear guidance on when to use this tool.

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

Deploy Server

crawl_start

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools