Refund order

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

Annotations already declare destructive=true, idempotent=false, openWorld=true, readOnly=false. The description adds genuine value beyond them: an approval gate ('Local approval required') and an explicit no-replay guarantee, both relevant to a non-idempotent destructive write. It stops short of describing irreversibility or failure/error behavior.

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 tightly packed sentences, front-loaded with the action, and every clause earns its place (partial vs full mode, approval requirement, no replay). No filler.

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 7-param tool with a nested payload and no output schema, the description covers intent, approval, and replay behavior but says nothing about what is returned, error conditions, or the payload/payload_file body-flag exclusivity surfaced in the schema. Annotations carry the safety profile, so this is adequate but with clear gaps.

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 description coverage is high (86%), and the schema itself documents the full_refund/amount mutual exclusion. The description reinforces the intent ('exact requested partial refund, or an explicitly named full refund'), nudging toward amount vs full_refund, but it adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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+resource (issue a refund on an order) and distinguishes two modes: exact partial refund vs explicitly named full refund. It does not, however, differentiate itself from the sibling refund_subscription_invoice, leaving the agent to infer that 'order' vs 'subscription invoice' is the dividing line.

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 conveys a precondition (local approval required) and a behavioral constraint (no automatic replay), which implies when the tool is safe to invoke. But it never names the alternative sibling (refund_subscription_invoice) or states the conditions that select one over the other, so alternative-routing guidance is left to inference.

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