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

Annotations declare a non-read-only, non-idempotent, open-world write, and the description adds substantial context beyond them: it creates a draft rather than a placed order, never charges a card, payment comes via a team-issued invoice/pay-link, production waits on proof approval, and retrying after a timeout risks duplicate drafts. That is exactly the extra behavioural detail annotations cannot carry.

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-loaded with the single most important fact (draft, not placed, no charge), then preconditions, retry warning, payment, and artwork. Every sentence addresses a real failure mode, though the final artwork sentence is long and carries parenthetical detail that could be tightened.

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 14-parameter, nested-object, mutation tool with no output schema, the description covers the workflow, safety posture, payment path and artwork policy well. The only real gap is what the call returns (beyond the hinted 'Review summary') and confirmation that the draft is what the team acts on next.

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 only 43%, so the description must compensate, and it does for the two highest-risk fields: `confirm` (call without it for a review summary; set true only after confirmation) and `artwork` (optional, never block an order on it, upload later via link or My Account). It does not, however, explain `customerType` payment-terms effects, `poNumber`, or the multi-line `items` behaviour that the schema itself documents.

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 first sentence gives a precise verb+resource ('Create a Shopify DRAFT order') and immediately disambiguates it from a placed order and from card charging. An agent can distinguish this from siblings like vivid_accept_quote, vivid_reorder and vivid_request_quote without opening any 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?

Explicit preconditions are given (summarise product/quantity/config/price/customer/delivery and obtain explicit confirmation before calling), plus a two-step invocation protocol: call without confirm for a Review summary, set confirm:true only after the customer confirms. It also names a failure mode to avoid ('Do NOT auto-retry after a timeout without first checking whether a draft was already created').

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