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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds the API version and endpoint path, which is modest extra context, but says nothing about what happens on a miss or on multiple ids being supplied.

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?

Two compact clauses plus the endpoint, with the identifier constraint front-loaded. The raw HTTP path is somewhat developer-facing but does reinforce the openWorld hint; nothing is wasted.

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 three-way identifier lookup with no output schema, the description should say what comes back (a full order object vs. a stub) and what a no-match looks like. Those are the remaining gaps; the input side is fully covered.

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 each of shopify_id / bigcommerce_id / custom_order_id is already documented. The description nevertheless adds a genuine constraint absent from the schema: exactly one identifier must be provided (the schema enforces no such mutual exclusion, and required parameters = 0).

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 — 'Find one order by a platform order id' — plus the concrete endpoint (GET /api/v3/merchant/shops/{shopId}/orders/lookup). It never contrasts itself with the sibling stamped_get_order, so the agent must infer that lookup is by external platform id while get is presumably by internal id.

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?

'give exactly one' conveys the key invocation constraint (mutually exclusive identifier choice), but there is no guidance on when to prefer this over stamped_get_order or stamped_list_orders, and no note about error behavior when no order matches.

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