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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuine context beyond that: it is keyless (no API key needed) and can perform optional RAG chunking, and it positions itself against Firecrawl/Jina. It still says nothing about crawl scope, page limits, rate limits, or how chunking affects output.

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?

The core sentence is duplicated verbatim after a truncated 'with….', which wastes the most salient position. The remaining line is marketing positioning ('keyless Firecrawl & Jina alternative') rather than operational detail.

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?

A crawler with a transparent nested input object and no output schema needs the description to explain input shape and crawl behavior; the description covers neither. An agent knows the outcome type but not how to configure or bound the crawl.

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?

There is one nested input object whose only documentation is 'See https://apify.com/noniner/website-to-markdown' – effectively no field-level semantics. The description adds nothing about the expected input (URL, crawl depth, chunking flags), so an agent has to open the external page or guess.

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 names a specific verb and resource ('Crawl any website or docs site into clean... Markdown') and adds the output flavor (LLM/RAG-ready, optional RAG chunking). It does not distinguish itself from overlapping siblings such as ai_web_extractor or ai_website_audit, but against the long tail it is unambiguous.

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?

'Crawl any website or docs site' implies the RAG/docs-ingestion use case, but there are no explicit when-to-use or when-not rules and no routing to any sibling, even though ai_web_extractor looks adjacent. Usage is inferable rather than stated.

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