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

Annotations already declare readOnly/idempotent/non-destructive, and the description usefully clarifies the semantic reason: it returns a link only, so no cart, order or payment exists yet, and shipping/discounts are resolved later at checkout. It also discloses a live behavior ('after checking current variants and availability') that annotations cannot express. It does not say what happens when a variant is unavailable.

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 the core behavior and the negative scope in the first two sentences with no filler. The trailing customer-support URL is slightly tangential but justifies itself by redirecting the 'existing orders' case it just excluded.

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, and the description correctly fills that gap by stating the return value is a link only and that totals/shipping/discounts are settled at checkout. What remains missing is failure-mode behavior when a variant is out of stock and how the agent should recover.

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 0%, so the description must carry the load; it conveys the 1–12 line ceiling and the 'one-time' meaning of items, plus that variant availability is checked. But per-line quantity max 6, the productId enum values, and the variantId numeric format are left entirely to the schema, and error behavior for stale variants is unstated.

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 artifact: 'Constructs an exact Shopify cart permalink for 1 to 12 one-time item lines.' This is clearly distinguishable from siblings like build_basket/build_box (which presumably build baskets/boxes) and open_shop, and the 'one-time' qualifier separates it from subscription flows.

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 explicit when-not conditions: 'does not create a cart, order, payment or subscription, and it does not handle recurring purchases or existing orders,' and redirects existing-order users to support. It stops short of naming the sibling tools an agent should pick instead (e.g., order_help, build_basket), leaving that routing to inference.

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