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

With readOnly/non-destructive already declared by annotations, the description still adds substantial context: IDs are enumerable without OAuth, the hash is unguessable, idempotency recovery is scoped to 24h on the same account, and provider refresh is throttled when the last check is under five minutes old. Those are behavioral traits no annotation conveys.

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 purpose, then callers, then recovery path, then return payload; sentences are dense and mostly load-bearing. It runs long and the return-value enumeration overlaps with the existing output schema, which slightly dilutes focus.

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?

Given four optional params, full schema coverage, an output schema, and read-only annotations, the description covers everything an agent needs: which key to use, what happens on timeout, and what a fulfilled eSIM/gift card response contains.

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; the description goes beyond it by explaining precedence (payment_link over checkout_hash), the OAuth constraint on order_id, and the timeout-recovery workflow where idempotency_key substitutes for a missing order_id. It doesn't add format specifics but adds real decision logic.

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 ('Check order or checkout status') and immediately segments the operation by caller identity (guest vs OAuth/PRO). It clearly signals this is a status-read tool distinct from create/preview siblings, though it never acknowledges the sibling 'guest_order_lookup', which could be a competing path for the same guest use case.

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?

Explicitly states which identifier to pass per caller type, marks payment_link as '(preferred)', and gives concrete prohibitions: don't pass sequential order_id without OAuth, don't ask the buyer for the hash, never re-create after a timeout. This is near-complete when/when-not/alternative guidance.

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