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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds meaningful context by flagging that these are *raw GraphQL* line items (unprocessed upstream payloads) and that one field is a resolved/derived value, but it omits error behavior, external-API failure modes, and any rate-limit or auth caveats expected of an open-world Shopify call.

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 sentences, front-loaded with the purpose and the returned field set, then the required inputs. The field enumeration is dense but each item carries identifying value; nothing is filler, though the list pushes toward the long side for a simple read tool.

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?

With no output schema, the description compensates by enumerating the fields returned, which is exactly what an agent needs to judge fit. Gaps remain around result shape (single order assumed? multiple line items?), pagination, and behaviour when the external Shopify id resolves to nothing, but the core contract is conveyed.

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%, so all three parameters are already documented, and the description largely restates them (shopId as ApiCredential.Id, order number examples) rather than extending them. The optional intentId correlation parameter is not mentioned at all, and no format constraints beyond the schema example are added. 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 ("Fetch raw Shopify GraphQL line items for an order") and enumerates the return payload fields (product, variant, SKU, customAttributes, product-linked flag, resolved material). This is clearly distinguishable from generic order tools like FetchWebshopOrder or FindOrder, though it does not name a sibling it is exclusive of.

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 second sentence tells the agent which identifiers to supply (shopId, order number like BU741087, or external order id), which is real usage guidance. It says nothing about when to prefer this over FetchWebshopOrder/FindOrder, nor when this tool is inappropriate (e.g. non-Shopify shops), so selection guidance remains implied.

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