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

Annotations only declare destructiveHint=true, but the description adds the critical facts: money moves to the original payment method, the refund is asynchronous with status pending, and there is no idempotency key so retries are unsafe. That is exactly the behavioral context the annotation does not 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?

Four short sentences, front-loaded with operation class and risk, then semantics, then the retry hazard. Nothing is wasted and the highest-risk information appears before the procedural detail.

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 two-parameter mutation with no output schema, the description covers the return behavior (asynchronous, status pending) and the safety constraint (no idempotency, verify via get_checkout_session first). An agent has everything needed to invoke it correctly and safely.

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 both parameters are already documented including the cents unit and the omit-for-full-refund rule. The description restates that same information without adding format or edge-case detail beyond the schema, so baseline 3 applies.

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 ('refund a paid Checkout Session to the customer's original payment method') and prefixes it with 'WRITE, MONEY' so the agent knows the operation class immediately. It is clearly distinct from the create/expire/get/list siblings.

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 says to omit amount for a full refund, and instructs the agent to call qashier_get_checkout_session before retrying, naming a concrete sibling and the condition that selects it. It also states a hard when-not: do NOT retry this call.

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