core_web_vitals_audit

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

With no annotations, the description carries the full burden and does so partially: it discloses the billing model (~$0.005 per result, charged to the user's own Apify account, free-plan price) and the row multiplicity per URL/device. It omits execution traits such as expected runtime, rate limits, or failure behavior on unreachable URLs, which matters for a bulk external fetch.

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 and dense — the audit scope and its outputs come first, with the cost caveat as a short second sentence. The first sentence is a long comma-run list of metric acronyms, which is slightly heavy but each element earns its place by telling the agent what results to expect.

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 no-output-schema tool, the description supplies the crucial return shape (one row per URL and device) and the billing implication of 'both'. Parameters are fully covered by the schema, so the only meaningful gap is the absence of runtime/rate-limit expectations for bulk audits.

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 100%, so all four parameters are already richly documented with examples, defaults, enums and rationale. The tool description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 — a bulk Core Web Vitals / PageSpeed audit via Lighthouse — and enumerates exactly the metrics returned (LCP, CLS, INP, TBT, top fixes). The scope 'one row per URL and device' distinguishes it from the sibling seo_page_audit by making clear this is a per-URL performance audit rather than a general SEO crawl.

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?

The description implies the tool's purpose but gives no explicit when-to-use vs when-not guidance and never names or contrasts with siblings such as seo_page_audit. The substantive usage advice (prefer mobile, performance category returns everything, 'both' doubles rows/billing) lives in the schema property descriptions rather than the tool description.

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