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

Goes well past the annotations: exact credit costs for standard vs premium proxies with and without JS, mandatory confirm, no automatic retries, truncation of large results, and a warning that returned text/HTML is untrusted website data. These are precisely the consequences an agent needs before spending credits.

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?

Front-loaded with the billable consequence, then prerequisites, then data-safety caveats – a sensible order with almost no filler. The all-caps labels and the confirm restatement are slightly noisy but each clause carries information.

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 credit-consuming, destructive-annotated tool with no output schema, the description covers cost, confirmation, retry behavior, truncation and data trust. The main omission is the shape of the returned matches (e.g. how per-element text/attributes come back), which is left implicit.

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?

With 67% schema coverage, the description adds real meaning: the 20-element cap, CSS vs XPath selector types, and how render_js/premium_proxies multiply the credit cost. It doesn't explain `country` or the per-element `attributes`/`html` options, but the schema covers most of those.

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: extract up to 20 CSS/XPath selectors from one public page. The scope limits (20 selectors, one public page) make it distinguishable from a full-page scrape, though it never names scrapeowl_scrape_page or scrapeowl_render_page as the alternatives.

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 cost/confirm mechanics and the 'one public page' scope, and the explicit 'Requires confirm:true' tells the agent a prerequisite. But it never says when to prefer targeted element extraction over the sibling scrape_page/render_page tools, so selection still requires inference.

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