Tulina

apify_website_crawl

Crawl a website and return the text of its pages as Markdown — for reading a whole site (docs, product pages, a blog), not one page. apify/website-content-crawler.

One page only? web_read is free and faster.

Returns — the LIST of pages with url, markdown, metadata (or {error, run_id, status, items}).

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": {
      "urls": "<urls>"
    },
    "name": "apify_website_crawl"
  }
}

Input Schema

Name	Required	Description
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`urls`	Yes	start URLs; the crawl stays under each one's path.
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`fields`	No	keep only these keys, e.g. `["url", "markdown"]`.
`_run_id`	No	OBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`max_depth`	No	link depth from the start URLs.
`max_pages`	No	pages to crawl in all.
`include_globs`	No	only crawl URLs matching these globs (`["https://example.com/blog/**"]`).
`max_total_charge_usd`	No	hard cost ceiling of the run, $5 by default, at most your organization's ceiling per run ($25 unless set otherwise).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It does add value by documenting the return shape (a LIST of pages with `url`, `markdown`, `metadata`) and the failure envelope `{error, run_id, status, items}`, and the "web_read is free" contrast hints that this call costs credits. However it never states that this is a paid actor run subject to the $5/$25 cost ceiling, nor latency, concurrency, or that a run_id/async run may be involved — significant omissions for an 11-parameter paid crawl with zero annotation coverage.

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 action and the sibling routing in the first two sentences; nothing is redundant padding. Minor deductions for the awkward indented "Returns —" block and the ambiguous parenthetical "(or `{error, run_id, status, items}`)", which reads as a partial fragment.

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

Completeness4/5

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

For a complex paid crawl with no annotations and no output schema, the description supplies the missing return contract and the key alternative, which covers most of what an agent needs to call it correctly. The gap is operational: cost ceiling behavior, run vs. sync execution, and expected duration are not addressed.

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 `max_depth`, `max_pages`, `include_globs`, `fields`, and `max_total_charge_usd` are already documented in the schema, and the baseline of 3 applies. The description adds no extra meaning about how depth, globs, or the cost ceiling interact with the crawl scope beyond noting each start URL's path bounds the crawl — which is in the schema too.

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?

States a concrete verb and resource ("Crawl a website and return the text of its pages as Markdown") plus the scope (whole site vs. one page) and even names the underlying actor. It explicitly contrasts with the sibling `web_read`, so an agent can separate the two without opening either schema.

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?

Gives both sides of the routing decision: use this for "reading a whole site (docs, product pages, a blog)" and use `web_read` when it's "one page only", with the trade-off spelled out (free and faster). This is exactly the when/when-not/alternative structure.

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

All Tulina tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?