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

Annotations only carry the safety profile (not readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: the order transitions to DISPUTED, the merchant has 7 days to answer by refunding, an unanswered dispute expires and damages merchant reputation (potentially suspending its quotes), and a verified refund resolves it. It even documents the 404 case for another identity's order.

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 action and eligibility, followed by state/constraint/error details. It is dense and every clause is informative, but the run-on semicolon structure is slightly harder to scan than a cleanly separated list would be.

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 an output schema handling return values, the description supplies everything else an agent needs: eligibility, the state machine, timing, consequences, cardinality limit, and the 404 failure mode. Nothing material for correct invocation 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?

With 0% schema coverage, the description carries the burden and does well: it enumerates the valid reason_code values, states the note length cap (1000 chars), and implies order_id refers to the buyer's own paid order. It adds real meaning beyond the bare schema, though order_id's expected format is still left implicit.

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?

"Open a dispute on an order" gives a specific verb and resource, and the parenthetical "(PAID..DELIVERED)" pins the exact precondition state. An agent can distinguish this from siblings like shop.order.cancel or shop.merchant.refund without opening any 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?

The description states the eligibility window (order must be PAID..DELIVERED) and the operational constraint (one open dispute per order), which is clear when-to-use context. It does not, however, explicitly contrast with shop.order.cancel or shop.merchant.refund as alternatives, leaving that routing to inference.

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