Skip to main content
Glama
r28ai

Web Research to Docs

by r28ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

firecrawl_scrape

Scrape a single URL and optionally extract information as markdown, HTML, screenshots, or structured JSON for reading or summarizing a specific webpage.

Instructions

Scrape a single URL and optionally extract information. Use when the user wants to read or summarize a specific webpage. Supports markdown, HTML, screenshots, and structured JSON extraction.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to scrape
proxyNoSpecifies the type of proxy to use.
maxAgeNoReturns a cached version of the page if it is younger than this age in milliseconds. The server applies 172800000 (2 days) when this is absent.
minAgeNoWhen set, the request only checks the cache and never triggers a fresh scrape.
mobileNoEmulate scraping from a mobile device.
actionsNoActions to perform on the page before grabbing the content.
formatsNoOutput formats to include in the response. Strings or objects. The server applies markdown when this is absent.
headersNoHeaders to send with the request.
parsersNoControls how files are processed during scraping.
profileNoPersistent browser storage across scrape and interact sessions.
timeoutNoTimeout in milliseconds. The server applies 60000 when this is absent.
waitForNoSpecify a delay in milliseconds before fetching the content. The server applies 0 when this is absent.
blockAdsNoEnables ad-blocking and cookie popup blocking.
locationNoLocation settings for the request.
lockdownNoServe from cache only and never make an outbound request. On miss, returns 404 SCRAPE_LOCKDOWN_CACHE_MISS.
redactPIINoRedact personally identifiable information from returned markdown. Pass true for defaults, or an object to tune it.
excludeTagsNoTags to exclude from the output.
includeTagsNoTags to include in the output.
storeInCacheNoIf true, the page will be stored in the Firecrawl index and cache.
auditMetadataNoUser attribution included with SIEM logging events when SIEM is enabled.
onlyMainContentNoOnly return the main content of the page excluding headers, navs, footers, etc. The server applies true when this is absent.
onlyCleanContentNoBeta. LLM pass over markdown to remove residual boilerplate that onlyMainContent can miss.
threatProtectionNoPer-request threat protection override. Enterprise feature.
zeroDataRetentionNoIf true, this will enable zero data retention for this scrape. To enable this feature, please contact help@firecrawl.dev
removeBase64ImagesNoRemoves all base64 images from the markdown output.
skipTlsVerificationNoSkip TLS certificate verification when making requests.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the agent knows this touches external state. The description adds the supported output formats, which is useful, but it omits behavior implied by the schema — that actions (click/write/executeJavascript) mutate the page, that storeInCache writes to an external index, and that some features cost credits. Nothing contradicts the annotations, but the added behavioral detail is thin.

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?

Three short sentences with the core purpose front-loaded and no filler. The trailing format list is somewhat redundant with the schema's formats enum, which keeps it short of ideal.

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 26-parameter tool with no output schema and only minimal annotations, yet the description is three sentences long. It omits cost/credit implications, caching/lockdown semantics, the relationship to firecrawl_extract, and any hint of what the response looks like, so an agent invoking it correctly still depends almost entirely on reading the schema.

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 all 26 parameters are already documented in-schema and the baseline is 3. The description echoes the formats dimension ('markdown, HTML, screenshots, structured JSON extraction') but adds no format syntax, precedence, or interaction detail beyond what the schema provides.

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 ('Scrape a single URL') plus an optional outgrowth ('optionally extract information'), so an agent can tell it is a per-URL content fetcher. The phrase 'a single URL' gestures at the multi-URL alternative but never names firecrawl_extract, so sibling differentiation is only implicit.

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?

It gives one clear trigger ('Use when the user wants to read or summarize a specific webpage'), which is real usage guidance. But it never states when NOT to use it, nor does it point to firecrawl_extract for bulk/structured extraction, so the routing decision against the closest sibling is left to inference.

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

Deploy Server

Other Tools