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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add what they cannot: VAT exclusivity, the definitional alignment with Shopify's Returns line, the booking month rule, and the deliberate exclusion of the current part month with the reason ('a part month reads as a drop'). That last point is exactly the kind of surprising behavior an agent needs to avoid misreading a result.

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 sentences, front-loaded with the metric definition, then the boundary rule, then usage, then the alternative. Every sentence carries distinct information; nothing restates the title or annotations.

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 zero parameters and no output schema, the description must carry the full definitional load, and it does: what is measured, over what window, on which basis, and what is omitted. An agent can call it and interpret the result correctly without further context.

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 no parameters, so the baseline is 4; the description correctly implies a fixed, non-configurable window rather than inviting date arguments. It does not explicitly say 'no filters accepted', which keeps it from a 5.

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+resource (refunds per month) and immediately pins the scope: last six complete months, amount refunded net of VAT plus refund count. It also names the sibling it is not (get_sales_breakdown) and the distinct basis (refund month, not order month), so an agent can separate it from the sales tools without opening a 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?

Gives explicit trigger utterances ('are returns going up', 'how much do we refund a month') and routes the adjacent use case elsewhere: 'For one period's returns beside sales use get_sales_breakdown.' Both when-to-use and the alternative are spelled out rather than implied.

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