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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real context: payment keys are returned masked, the provider is reported as connected and test-vs-live, and "Amounts are in major currency units" pre-empts a units mistake. It does not describe response shape or failure modes, but the redaction and unit conventions are genuinely useful disclosures beyond the annotations.

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?

The scope statement is front-loaded and the long enumeration that follows is dense but each item is a distinct capability an agent would otherwise have to guess at. The final sentence about units and the call-timing clause are both load-bearing. It is a wall of one paragraph, though — breaking the trigger guidance from the return-contents list would improve scanability.

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 full burden of explaining return contents, and it does so comprehensively — health/gating fields, currency, payments with key masking, COD limits, shipping zones and rates, tax including India GST/GSTIN and tax-inclusive pricing, and discounts. An agent knows exactly what questions this call will answer before invoking it.

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 coverage is 100% with only two parameters, both fully described in the schema (site_id sourced from `list_sites`, user_goal with an example and a privacy caveat). The description adds nothing about either parameter, which is acceptable — baseline 3 applies when the schema does the heavy lifting.

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 opens with a precise but non-verb framing — "Everything that decides whether an online store can sell" — then enumerates the exact data returned (cart state, can_take_payment, missing/recommended steps, currency, payment provider, COD, shipping, tax, discounts). That scope is unmistakably e-commerce, which distinguishes it from the general `get_site_settings` sibling even though that sibling is never named. Clear, but a single clause naming the boundary against `get_site_settings` would earn the top score.

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?

Explicit call timing is given: "Call it before publish_site on any site with products or a cart, and after changing these settings." That is a concrete, actionable trigger tied to a named sibling (`publish_site`) and to the configure_* mutation tools. No explicit when-not-to-use or named read alternative, so it stops short of a 5.

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