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

Annotations (readOnly=false, openWorld=true) are present and not contradicted. The description adds behavioral notes beyond the flags: the URL-to-variant resolution 'happens automatically — no catalog import needed' and the result is a direct, clicking Shopify checkout link; that gives the system a clear model of what invokaking the tool accomplains. It doesn't mention the authority-gated decision_id path, but the schema documents that case, so the safety profile is covered.

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?

Four sentences, each earning its place: core purpose, the auto-resolution behavior, the supported feature set, and a guardrail plus return format. It is front-loaded with the most important information and keeps feature listing to one sentence. Only a minor polish benefit would come from more trimming.

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?

For a 5-parameter, no-output-schema tool, the description covers the essential agent decision: what the tool does, when to use it, how to route (URLs vs variant IDs), and what is returned (a Shopify checkout link). The authority-gated requirement (decision_id) is a niche configuration left to the schema; the description handles the common path completely.

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% — all 5 parameters (items, product_urls, note, discount_code, decision_id) already have meaningful descriptions, defaults, and constraints documented. The description adds framing that HTML and URL inputs are complementary and that URLs auto-resolve, which is helpful but not required to compensate for any coverage gap. 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?

States a specific verb and resource: 'Create a checkout URL for one or more products.' The sentence 'Do not use unless the user wants to buy — use search_products or skincare_recommend first' sharpens the boundary with the sibling recall/recommend tools, so an agent can select this tool without opening its schema.

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?

The description gives explicit when-not-to-use guidance ('Do not use unless the user wants to purchase') and names alternatives to call first (search_products, skincare_recommend). It also explains that both variant IDs (items, product URLs (product_urls) are acceptable inputs, so there is no ambiguity about how to assemble the call.

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