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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely useful operational context the annotations do not: results are cached for 30 minutes and the tool is rate limited per client, plus it discloses what data sources are fetched.

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 tight sentences that front-load the core capability before the operational caveats. Every clause carries information — scoring range, inputs, what is returned, and the caching/rate-limit constraints — with no filler.

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?

No output schema exists, but the description still conveys the return shape ('top issues with how to fix them') and the scoring range, and it flags caching that could surprise an agent re-calling after a change. Coverage is good for a two-parameter read tool, with only minor gaps around error behavior for non-Shopify or private URLs.

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 parameters (store_url, language enum with default) are fully documented in the schema. The description adds nothing about parameter formatting or the effect of the language option, so the baseline 3 is correct.

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 with scope: scores a public Shopify store 0-100 for AI shopping assistants, and names the exact inputs it inspects (public catalog, robots.txt, policy pages, structured data). This is clearly distinguishable from the sibling explain_issue and get_surfaced_plans tools.

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 scoring framing — you'd call it to audit a store — but the description never states when to use it versus the siblings, nor any preconditions (e.g. that the store must be publicly reachable). 'Read-only' is the only routing-ish guidance and that is already in annotations.

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