Skip to main content
Glama

firecrawl_map

Discover and list all URLs of a website starting from a base URL to explore its structure or locate specific pages.

Instructions

Discover and list all URLs of a website starting from a base URL. Use when the user wants to explore a site's structure or find specific pages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe base URL to start crawling from.
limitNoMaximum number of links to return. The server applies 5000 when this is absent.
searchNoSpecify a search query to order the results by relevance. Example: 'blog' will return URLs that contain the word 'blog' in the URL ordered by relevance.
sitemapNoSitemap mode when mapping. If you set it to `skip`, the sitemap won't be used to find URLs. If you set it to `only`, only URLs that are in the sitemap will be returned. The server applies `include` when this is absent.
timeoutNoTimeout in milliseconds. There is no timeout by default. Milliseconds, not seconds: 30000 is thirty seconds, and 30 fails instantly.
locationNoLocation settings for the request.
ignoreCacheNoBypass the sitemap cache to retrieve fresh URLs. Sitemap data is cached for up to 7 days; use this parameter when your sitemap has been recently updated.
auditMetadataNoUser attribution included with SIEM logging events when SIEM is enabled.
threatProtectionNoPer-request threat protection override. Enterprise feature.
includeSubdomainsNoInclude subdomains of the website. The server applies true when this is absent.
ignoreQueryParametersNoDo not return URLs with query parameters. The server applies true when this is absent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

Annotations already declare openWorldHint=true, and the schema itself discloses the practically important behaviors (7-day sitemap cache, ignoreCache to bypass it, timeout in milliseconds, default limit of 5000). The description adds no behavioral context beyond 'list all URLs' and is silent on cost, latency, rate limits, or whether the result is bare URLs or URL+metadata.

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?

Two sentences, no filler, and the core capability is front-loaded before the usage hint. Every sentence earns its place.

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?

With 11 parameters, no output schema, and no annotations describing the return value, the definition is serviceable but thin at the top level. The schema compensates heavily for parameter behavior, yet nothing tells an agent what a successful map actually returns (URL list shape, ordering, whether it is paginated).

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% and all 11 parameters carry their own prose, including defaults the server applies when omitted. Baseline 3 applies; the description contributes no additional semantic guidance about any parameter such as search, sitemap mode, or limit.

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 a specific verb and resource: 'Discover and list all URLs of a website starting from a base URL.' That is unambiguous on its own. However, it never distinguishes itself from firecrawl_crawl or firecrawl_scrape, which are adjacent in the sibling list and do partially overlapping work.

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?

'Use when the user wants to explore a site's structure or find specific pages' gives a usage context, so it is more than implied. But it names no alternative and offers no exclusions, which is a real gap given firecrawl_crawl (get URLs plus page content) and firecrawl_scrape (single page) sit right beside it.

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