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

With no annotations, the description carries the behavioral burden and does well: it discloses the read of Stripe state, the side effect of saving a private dated observation, the no-money-movement constraint, and API-key/role requirements. It leaves some operational details unstated, such as failure behavior, idempotency, or exactly what observation is stored.

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 description is three compact sentences with the core purpose and key safety constraint front-loaded. Every sentence adds useful information, and there is 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?

The description adequately covers purpose, role/auth requirements, and the critical no-refund/no-money-movement behavior. But with no annotations, no output schema, and no schema parameter descriptions, it remains incomplete on parameter meaning and the returned Stripe/refund state an agent would receive.

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 sole parameter, issue_id, has zero schema description coverage, so the description needs to compensate. It does not mention issue_id or explain what value should be supplied beyond the loose implication that it identifies an existing recorded refund issue.

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?

The description gives a specific verb and resource: reading Stripe state for an existing recorded refund. It also clarifies the operation is not creating a refund or moving money, which helps distinguish it from refund-creation behavior. It does not explicitly distinguish itself from close siblings such as get_delivery_receipt or save_delivery_receipt.

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?

It states the relevant context clearly: buyer or admin, existing recorded refund, and API-key requirement. The phrase 'never creates a refund' also excludes refund-creation use cases. However, it does not name alternative tools or describe when another sibling should be used instead.

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