Skip to main content
Glama

Start Crawl Job

crawl
Read-only

Start a bounded local web-scraping job that respects robots.txt and returns a job ID immediately.

Instructions

Start a bounded Firecrawl Local Crawl Job. Respect for robots.txt is mandatory. Returns immediately with a crawlId.

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": "crawl"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
limitNo
delayMsNo
formatsNo
sitemapNoinclude
timeoutMsNo
waitForMsNo
excludePathsNo
includePathsNo
maxConcurrencyNo
allowSubdomainsNo
onlyMainContentNo
crawlEntireDomainNo
maxDiscoveryDepthNo
allowExternalLinksNo

Output Schema

NameRequiredDescriptionDefault
pagesYes
totalYes
errorsYes
offsetYes
statusYes
crawlIdYes
hasMoreYes
partialYes
returnedYes
completedYes
expiresAtNo
artifactIdNo
providerJobIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is partly covered. The description adds meaningful behavior beyond that: the job is bounded, robots.txt compliance is mandatory, and the call returns immediately with a crawlId. It still omits important operational context such as authentication, rate limits, failure behavior, and what 'bounded' means in practice across the 15 parameters.

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 three short sentences with the primary purpose front-loaded. Every sentence adds a distinct fact: what is started, the robots.txt constraint, and the immediate return value. There is no filler.

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

Completeness2/5

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

This is a complex, open-world tool with 15 parameters, and the description is far too thin for that complexity. The output schema covers return values and annotations cover safety, but the description provides no parameter semantics and no usage guidance for choosing between crawling and the other discovery tools.

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

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 15 parameters, and the description does not explain any of them. It mentions only 'bounded' and 'crawlId', leaving url, limit, delayMs, formats, include/exclude paths, concurrency, subdomain/main-content/depth flags, and the rest entirely undocumented beyond their names and raw schema constraints.

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 names a specific verb and resource: 'Start a ... Crawl Job.' It adds useful scope with 'bounded' and clarifies that it returns a crawlId. It does not explicitly distinguish itself from siblings such as fetch, map, or search, but the crawl-job framing is clear.

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?

There is no explicit guidance on when to use this tool versus fetch, browse, map, or search, nor when a crawl is preferable to a single-page operation. 'Returns immediately with a crawlId' hints at an asynchronous workflow and a follow-up status check, but it never states that the agent should poll crawl_status or cancel via crawl_cancel.

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