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

Annotations already cover read-only/non-destructive/open-world, so the bar is lower, and the description still adds two genuinely useful traits: the 1-credit cost and the degradation path when a site blocks automated readers (PageSpeed still runs, result flags the page as not read). It does not say whether the call is synchronous or how long a PageSpeed run takes, which is the remaining behavioral gap.

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?

Three tight sentences, front-loaded with the deliverables, followed by the failure-mode caveat and the cost. The long pixel parenthetical is dense but every clause carries information an agent needs; nothing is padding.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the data categories returned, plus the blocked-page outcome and cost. It does not mention device/viewport context for the PageSpeed score or expected latency, but for a 2-parameter read tool this is close to complete.

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 both 'brand' and 'competitor' are already documented with examples and semantics. The description adds no parameter-level detail beyond the schema, so baseline 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?

The description names a specific verb+resource ('audit the competitor's home page') and enumerates exactly what it extracts: PageSpeed scores, LCP, headline, CTAs, forms, and a specific list of tracking pixels. It is clearly distinguishable from siblings like teardown or serp_snapshot without opening any schema.

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 naming 'the competitor's home page' as the target and by the 1-credit cost note, but the description never states when to pick this over teardown, competitor_ads_google, or other audit-adjacent siblings, nor any prerequisites such as needing the competitor to have a live site.

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