shopify_list_abandoned_checkouts

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

The description adds real behavioral value beyond the annotations: it discloses that responses are private, that it 'always fetches fresh provider data' (not cached), and critically that 'supplied replay identity is rejected' — a concrete consequence of the non-idempotent hint that an agent would not infer from the schema alone. This is genuinely useful operational context, and it is consistent with readOnlyHint=true, openWorldHint=true, and idempotentHint=false.

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?

Well-structured and front-loaded: purpose and use case in one sentence, then a two-sentence behavioral note, then a compact Args block. Every line earns its place — the idempotency-key warning and the effect constraint look unusual but both carry information that prevents invocation errors. No filler or repetition of schema-visible type/required info.

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 an 8-parameter tool with 0% schema coverage, the description covers everything an agent needs to select and call it correctly: purpose, use case, fresh-data behavior, replay-rejection, pagination mechanics, query syntax, and the effect invariant. An output schema exists, so return-value documentation is not required. Nothing material is missing.

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 0%, so the description carries the full burden — and it delivers. All 8 parameters get semantic enrichment: limit gets a 1-20 range, query gets a concrete syntax example ('created_at:>=2026-04-01'), cursor gets its pagination role ('from the previous page's next_cursor'), and effect gets a hard constraint ('Required and must be read; Spring verifies it'). This fully compensates for the empty schema.

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 description opens with a specific verb+resource: 'List the shop's recent abandoned checkouts with cart subtotals and customer context.' It names the returned content and a concrete downstream use case ('compute abandoned-revenue at risk and prioritise recovery'). The resource 'abandoned checkouts' is a distinct Shopify concept that keeps it clearly separable from sibling list tools like shopify_list_draft_orders or shopify_list_refunds.

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 a clear invocation context: 'Use to compute abandoned-revenue at risk and prioritise recovery.' This tells the agent when the tool is the right choice. It does not, however, name explicit alternatives or state when-not-to-use conditions, so it stops short of full exclusionary guidance.

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