crawl

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

With no annotations provided, the description carries the full burden and largely meets it: it discloses the BFS algorithm, max_depth/max_pages limits, internal-link scope, the '--- URL:' output separator, and caching behavior. These are useful operational traits beyond what the bare schema provides.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Core behavior is front-loaded, and the labeled WHEN/NOT WHEN blocks make the description scannable and actionable. The phrase 'Паттерн Firecrawl crawl' is cryptic and adds little, but overall the description is economical and well organized.

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

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

The description covers the algorithm, limits, output format, cache behavior, and alternative tools, and an output schema exists for return details. However, missing semantics for max_chars and article_only are a real gap for a six-parameter tool with no annotations and no inline schema descriptions.

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

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

Schema description coverage is 0%, so the description must compensate. It explains max_depth and max_pages and hints at pattern, but it never defines max_chars or article_only, both of which are non-obvious and defaulted. The schema only offers names and defaults, so an agent would have to guess those meanings.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description defines crawl as a BFS traversal of a site from a start page following internal links, with explicit depth/page caps and a text-plus-delimiter output. This clearly distinguishes it from siblings like map_site/sitemap (URL-only) and fetch_page (single section).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It includes explicit КОГДА and НЕ КОГДА blocks: use crawl for full-site text collection; use map_site/sitemap for URLs only, fetch_page for one section, and sitemap + pattern filtering for huge sites. This is direct routing guidance naming alternatives and conditions.

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