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

With no annotations, the description carries the behavioral burden and does add real signal: deterministic oldest-first ordering, cursor continuation via next_cursor, and the narrowed scope when system+unsynced are combined. It omits rate limits, max page size behavior, and what happens on an invalid/expired cursor, so it is not fully self-sufficient.

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?

Three dense sentences, front-loaded with what the tool returns before the scheduling and filter caveats. Every sentence carries content; only 'outside ids' jargon costs a little comprehension.

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?

An output schema exists, so return shape and next_cursor need not be explained, and the description correctly focuses on semantics. Remaining gaps (limit/backfill behavior, no-cursor first-run behavior, error cases) are modest for a polling cursor tool.

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% across 7 parameters, so the description must compensate. It explains the semantics of cursor, updated_since, system, and unsynced, and implies kinds via the record-type list, but leaves limit and shop_id unexplained — roughly half the parameters get added meaning.

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 states a specific resource set (invoices, payments, refunds, customers), the delta semantics ('changed since a time or cursor'), and the ordering ('oldest change first'). It is clearly an incremental change-feed tool, distinguishable from list/get siblings, though it never names the related sync_findRefs or sync_setRef siblings.

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?

'Run it on the shop's own schedule and save next_cursor for the next run' gives operational guidance, and the unsynced/system condition is spelled out. But it gives no explicit when-to-use-vs-alternative routing (e.g., versus sync_findRefs or webhooks for push-based flows), and no statement of what a first run without a cursor does.

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