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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: cursor invalidation on order version change, that live pages do not freeze a mutation target set, that recorded unit amounts carry unknown currency, that listing IDs appear only when the linked copy still belongs to the store, and that no buyer or payment data is returned. It also discloses OAuth scopes, live MANAGE_ORDERS permission, and the failure modes for invalid fields, unavailable stores, foreign/deleted targets and provider errors.

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?

The core constraint is front-loaded, but the description is padded with sentences that do not earn their place: auth is stated twice ('Requires OAuth store:read consent. Requires store:read consent, a currently approved owned store and live MANAGE_ORDERS permission'), and 'Use supercatch_list_order_items for this read in the connected account' restates the tool name. The dense list of negations ('No prices, inventory, orders, automation...') is hard to parse and could be compressed.

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 the description needn't detail return values, and it still sketches the envelope shape and its explicit scope/provenance/omissions. Across pagination, permissions, data withholding, error semantics and cursor expiry, nothing an agent needs to call this correctly 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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: it states the 20-line ceiling in prose, that the target must be one exact owned order, and crucially that changed order versions expire the cursor, which refines the schema's 'same ... version' wording with the consequence of violating it.

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 opening sentence gives a specific verb and resource: 'Traverse at most 20 lines of one exact owned order,' which tells an agent this paginates line items within a single order. It is scoped precisely enough to distinguish from supercatch_get_order or supercatch_list_store_orders, but it never names those siblings or states the distinction explicitly, and the later sentence 'Use supercatch_list_order_items for this read' merely restates the name.

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?

It gives operational continuation rules ('Keep the same order, connection, actor and page size; changed order versions expire the cursor' and 'Expired cursors require a fresh search'), which implicitly tells the agent how to use it across pages. However, there is no explicit when-to-use-this-versus-supercatch_get_order guidance, and no statement of when listing order lines is the right choice over fetching the full order.

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