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

Even though annotations already show this is a write operation, the description adds highly valuable behavioural context: it creates a DRAFT only, never charges a card, payment comes later via secure invoice/pay-link, production waits on proof approval, and retrying risks duplicate drafts. No contradiction with 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?

Two dense but focused sentences: the most important distinction (draft vs. final/no charge) is front-loaded, and every clause carries actionable guidance. No filler, repetition is purposeful for safety-critical behaviour.

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 tool with no output schema and non-idempotent behaviour, the description covers the essential invocation protocol, the retry hazard, the payment/production implications, and what kind of response to expect before confirmation. The nested object details are delegated to the schema, which is an appropriate split.

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 only 43%, and the description does not document every parameter. However, it gives important confirm semantics, explains what must be included in the payload (product, quantity, config, customer details, delivery/pickup), and clarifies that contact, delivery, and PO stay at the top level. This partially compensates for weak schema coverage, but many simple fields remain inferred rather than described.

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?

Description states exactly what the tool is for: 'Create a Shopify DRAFT order for Vivid Ads team review' and immediately clarifies what it is NOT: a final/placed order that charges a card. This makes it easy to separate from sibling quote, status, and fulfilment tools.

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?

Very strong workflow guidance: call without confirm to get a review summary, pass confirm only after explicit customer confirmation, and never auto-retry after a timeout without checking whether a draft was already created. It does not explicitly name alternative sibling tools for related decisions, but the when/when-not guidance is otherwise explicit.

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