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

Annotations already declare read-only/idempotent/non-destructive, and the description adds substantial beyond-annotation context: refunds cannot be created, changed or canceled by any MCP tool, amounts are negative and VAT-inclusive in USD, ordering is most-recent-first with pagination, and the completed-only visibility rule. This is rich behavioral disclosure.

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 key scoping constraint (completed only, read-only) is front-loaded and most sentences carry distinct information. It is a single dense block with some redundancy — the refund concept is defined twice ('money actually returned' then 'money returned to the customer') — which keeps it just short of a 5.

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 compensates by enumerating the return fields (id, refund_target, destination, amount, currency, reference, refunded_entities, credited_to_balance, timestamps, pagination meta) and explaining destination/credited_to_balance semantics. Nothing an agent needs to call or interpret it 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?

Schema description coverage is 100%, so the schema already documents page, page_size, created_after and created_before with defaults and formats. The description only restates that creation-time filtering is optional, adding no syntax or semantics beyond the schema — 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 (list the authenticated customer's COMPLETED refunds) and immediately scopes it to money actually returned. It defines what a refund is and the two issuance pathways, so an agent knows exactly what this tool returns versus a generic payment/order listing.

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?

Gives clear context: only completed refunds appear (same as the panel), in-progress refunds should be handled by telling the user to check back or contact support, and refunded_entities references can be cross-referenced with list_payments / list_orders. It stops short of explicitly naming a sibling list tool to use instead for other refund states.

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