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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds meaningful context beyond that: the score is heuristic, output is capped at ≤10 gaps, no login is required, and WAF/CDN blocking is outside its detection scope.

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?

A single dense sentence that front-loads the action and scope, then the return value, then the caveats. Every clause earns its place with no 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 responsibility for describing the return value, and it does so precisely (0–100 score plus ranked gaps and fixes with named check categories). The only missing item, a sample output shape, is not essential for correct invocation.

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?

Only one parameter (store_url) and schema coverage is 100%, including the local-path override detail, so the schema does the heavy lifting. The description adds nothing about the URL parameter beyond 'public store homepage', 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?

Uses a specific verb+resource ('Audits a public store homepage') and enumerates exactly what is crawled (homepage, robots.txt, sitemap, one sampled product page) and what is returned (0–100 heuristic score, top ≤10 gaps and fixes). This scope is distinguishable at a glance from the product-page-focused sibling audit_product_page.

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?

Clearly frames the tool as a read-only, no-login audit and states a limitation ('does not detect WAF/CDN bot blocking'), which tells the agent when results may be misleading. It never names a sibling or explicitly says when to prefer audit_product_page or the feed-validation tools instead, so the alternative-routing guidance is implicit.

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