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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context on top: cursor paging, the 20-order cap for the detail view, that 'payable' marks a placed-but-unpaid order, that unpaid orders carry pay_link, and that the answer self-reports coverage and how to fetch the remainder. Authentication mechanics (Bearer mo1_… or the ref argument) fill the gap left by the absent auth annotation.

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-loads the resource and scope, then separates the two views with a semicolon-delimited structure that maps onto the view enum. It is dense and slightly run-on, but every clause (status list, date filter, cursor, 20-order cap, pay_link) carries information rather than filler.

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 carries the return-shape burden and does so: field-level expectations for the list view (status, dates, totals) and the detail view (lines with live price and stock, totals, shipping, payment, tracking, addresses). Limits, paging, auth, and partial-result behavior are all covered, which is complete for an 8-parameter read 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 coverage is 88% so the baseline is 3, but the description goes further by explaining the otherwise-undocumented 'view' enum (what 'orders' returns vs. what 'order' returns) and by restating status values and filtering semantics in prose. It adds genuine meaning beyond the per-property descriptions rather than duplicating them.

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?

Opens with a specific verb+resource ('The shopper's earlier orders with this store') and then splits the two modes precisely: 'orders' as a filtered, cursor-paged list and 'order' as up to 20 full orders by id. An agent can tell this apart from start_order, place_order, or check_payment without inspecting the 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?

Gives concrete usage intent ('Use it to reorder or answer questions about earlier orders') and states the prerequisite (the order reference from start_order via Bearer or ref). It does not name which sibling to use instead for adjacent needs such as payment status (check_payment) or cart changes (edit_cart), so routing guidance is clear but not exhaustive.

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