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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description adds the caller-scoped boundary (only the authenticated customer's records) and the explicit negative capability. It does not say anything about result volume, ordering, or whether refunds are always present, which are minor residual gaps.

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 short sentences, no filler, and the operative scope statement is front-loaded ahead of the exclusion. Every clause carries information an agent would otherwise have to guess.

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 parameters, no output schema and full annotation coverage, the description supplies exactly the scope and capability boundaries an agent needs to select it. It could be slightly richer about what an 'order' record or 'refund state' contains, but the essential decision information is present.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing parameter-related that the description needs to compensate for. The mention of 'refund state' is a bare hint about the result shape rather than parameter semantics.

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 (read) and resource (the authenticated customer's token orders and refund state), with the scope explicitly limited to the caller's own data. The negative clause ('cannot purchase tokens') further sharpens what the tool is, distinguishing it from checkout/purchase siblings and from get_my_token_wallet.

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 rules out two adjacent intents (purchasing tokens, obtaining checkout links), which is real when-not-use guidance rather than implied. It stops short of naming the sibling to use instead (e.g., a purchase or wallet tool), so the routing is left slightly to the agent.

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