Scrape as Markdown

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

Adds real behavior beyond the annotations: very long pages are truncated and `tokenLimit` can lower the cap, and it discloses the upstream dependency (Decodo `universal` target). It doesn't mention rate limits, cost, or failure modes for blocked/private pages, keeping it short of 5.

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?

Two tight sentences: capability first, then the routing rule and truncation caveat, plus a docs link. Nothing repeated from the title and no filler.

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?

For a read-only single-URL scraper with a fully described schema and no output schema, the description covers what's returned (Markdown) and the main length constraint. Minor gaps: it doesn't say how failures (paywalls, JS-only pages, crawling restrictions) manifest, though jsRender in the schema hints at the JS case.

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 coverage is 100%, so geo, locale, jsRender, and url are already fully documented. The description only reinforces tokenLimit behavior, which the schema also states; baseline 3 is appropriate when the schema carries the parameter burden.

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?

Names a specific verb (fetch) and resource (any public web page via the Decodo Web Scraping API `universal` target) and states the output format (Markdown). This clearly distinguishes it from site-specific siblings like amazon_product or youtube_metadata.

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?

"Use it to read a specific URL when no site-specific tool fits" gives an explicit selection rule against the many site-specific siblings. It lacks a stated when-not (e.g., dynamic JS-heavy pages needing jsRender, or bulk crawling where crawl_start applies), so not quite a 5.

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