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

No annotations are provided, so the description carries the full burden. It adds genuinely useful non-schema context — cost per call and the 3-free-calls-per-day limit without an API key — which is exactly the kind of behavioral detail annotations would otherwise supply. It still omits that the operation is a read-only fetch, whether auth is required for full access, and whether results are paginated or capped.

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 sentences, no padding, with the output definition front-loaded and the pricing constraint placed after. The only waste is that the title restates the first sentence almost verbatim, so the opening clause is largely duplicated rather than additive.

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 21-parameter, zero-annotation, no-output-schema scraping tool, the description covers only the two filter flags and the price. It leaves the url-vs-html input choice, rendering and wait behavior, and auth requirements unaddressed, so an agent cannot call it correctly on the first try without reading the schema in full.

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?

21 parameters at 19% schema description coverage means the description must compensate, and it only maps to two of them (excludeExternalLinks via 'same-domain-only', visibleLinksOnly via 'visible-only'). The other 19 parameters — cookies, viewport, userAgent, gotoOptions, waitForSelector, bestAttempt, authenticate, and the url/html mutual exclusion — receive no explanation in the description.

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?

States a specific verb and resource: extracts 'every link on the page as absolute URLs', with the two result-shaping options named. The resource ('links') clearly contrasts with siblings markdown, pdf, screenshot, and snapshot, so an agent can pick it without opening the schema. No sibling is named explicitly, keeping it short of a 5.

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?

Usage is implied by the narrow resource: use this when you want link URLs rather than rendered content. However, there is no explicit when-to-use versus markdown/snapshot guidance, no exclusions, and no mention of when the same-domain or visible-only filters should be applied. Adequate but leaves routing to inference.

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