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

Annotations supply destructiveHint=true, and the description reinforces it while adding genuinely new behavior: the settled/settling precondition, money movement direction, the GraphQL mutation name, and the full-vs-partial refund semantics. It does not mention irreversibility limits, permission requirements, or failure behavior (e.g. refunding an already-refunded charge), which would be the remaining useful context.

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 compact sentences, front-loaded with the DESTRUCTIVE warning and the eligibility constraint before operational detail. The leading 'DESTRUCTIVE' and the mutation name are mildly redundant with the annotation, but nothing 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?

For a two-parameter mutation with no output schema, the description covers everything needed to invoke it correctly: eligibility, argument omission rules, amount format expectation, and the sibling alternative. Return-value detail is unnecessary because no output schema is exposed.

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 100% and both the amount format (decimal string) and the 'omit for full refund' rule are already documented in the schema and pattern. The description restates rather than extends parameter meaning, so the 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 transaction) plus the critical scope constraint: only SETTLED or settling transactions. It names the sibling it must not be confused with (braintree_void_transaction) and the underlying GraphQL mutation, so an agent can select it without opening the 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?

Explicit routing rules: use this for settled transactions, use braintree_void_transaction for unsettled ones, omit `amount` for full refunds and pass a decimal string for partials. Both the when and the when-not are stated with the alternative named.

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