Get transaction

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

Annotations already declare this a read-only, idempotent, non-destructive call, and the description adds substantive behavior beyond that: payment provider data is never returned, contact fields stay redacted unless include_contact_details is set, barcode codes are gated, and ticket-item/note payloads are paged via sub-resources. That is exactly the extra context annotations cannot carry.

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 identification ('One transaction ... by its txn_ id') is front-loaded, and the second sentence carries the conditional-access rules. It is dense — a long mid-sentence enumeration of returned sub-resources — but nearly every clause conveys a field set or a gate, so little 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?

With no output schema, the description correctly assumes the burden of describing the return payload: identity fields, totals, line-item types, coupons, notes and paging sub-endpoints, plus redaction and payment-provider exclusions. An agent can anticipate the shape of the response without a return schema.

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?

With 60% schema description coverage, the schema documents include_barcodes, include_contact_details and transaction_id, but leaves max_notes and max_ticket_items undocumented there. The description compensates by explaining the contact-detail redaction and barcode gates and by signaling that ticket-item and note collections are paged, though it does not explicitly explain the two max_* limits.

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 ('One transaction ... by its txn_ id') and enumerates the returned content: status, reference, totals, customer name, ticket items, coupons, notes. This is clearly distinguishable from siblings like get_visit and get_event because it names the transaction resource and its txn_ identifier.

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?

Usage is implied by the 'by its txn_ id' framing and the explicit gates on include_contact_details/include_barcodes, but the description never says when to prefer this tool over a sibling such as get_visit or when a lookup should be avoided. No explicit when-not guidance or named alternative.

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