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

Annotations already flag readOnly/idempotent/non-destructive, and the description adds substantial context on top: real Shopify basket is created but no order is placed or payment taken, prices/discounts are Shopify's exact live readback, and gifts follow a stated box-count ladder. It also discloses a return-driven branch (need_shirt_size) and that one-time results include the subscription alternative.

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-loads what the tool produces (basket + checkout link) and the routing intent, then adds constraints. The gift ladder and subscription-upgrade detail are the longest stretch, but they carry real user-facing value and remain compact; no filler sentences.

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, yet the description covers the return payload (checkout link, need_shirt_size branch, live pricing, subscription comparison) and the no-payment boundary. The remaining gap is the items/packCans semantics and basket-size limits, which an agent must infer from the schema alone.

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?

With 0% schema description coverage the description must carry the schema, and it explains frequency (one-time vs subscription) and shirtSize (S-4XL, only when need_shirt_size is returned). However, the nested items array is barely addressed: packCans is never mentioned and the quantity 1-6 and max-6-items limits are left entirely to the schema.

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?

Names a specific verb and resource ('Builds a real IMPOSSIBREW Shopify basket') and states its output ('returns a checkout link'). 'Suits any request to buy, order, try or subscribe' routes intent away from browse/compare siblings, though it never names build_box or build_shop_link, the closest potential overlaps.

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?

Gives clear triggering intent ('any request to buy, order, try or subscribe') and an explicit boundary ('It does not place an order or take payment: the customer completes checkout on impossibrew.co.uk'). It also sequences a follow-up call ('A T-shirt size is needed only when the result says need_shirt_size'), but never names an alternative tool or when to prefer one.

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