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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds substantial value on top by disclosing the mandatory two-step preview/confirm protocol, the preview_id handshake, the 5-minute-to-90-day window for apply_at, and the refund exclusion. It loses a point for the garbled phrase 'a note (private, (private notes only))', which muddies whether notes are always private or conditional on note_to_customer.

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-loaded with the core action and workflow, and nearly every sentence carries operational meaning. The final sentence is a dense run-on mixing confirm, preview_id and apply_at, and the doubled-parenthesis note phrase is sloppy.

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 a destructive, open-world mutation with annotations covering the safety profile and no output schema, this gives the agent the full call sequence, constraints, and exclusions. It omits what the preview response actually contains (what to show the user) and whether status/order_id are effectively required, which a careful agent would still need to infer.

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 63%, so the description must carry part of the load; it does explain the confirm/preview_id pairing and the apply_at bounds and time semantics beyond the schema's field-level text. It still never explains status enum consequences or the store parameter's role, so it only partly compensates for the coverage gap.

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 — changes an order's status and/or adds a note — and rules out one adjacent operation by declaring refunds must be handled in PrestaShop. An agent can distinguish this mutation from the read-side siblings (get_order, find_orders) without opening 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 an explicit workflow (preview first, then confirm), the human-in-the-loop requirement (always show the preview, get explicit approval before calling with confirm=true), the deferred-application variant, and the exclusion (refunds done elsewhere). No inference is left to the agent.

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