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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: sort order (newest first), the absence of a date filter and of a total count, and the workflow constraint that refunds originate on the POS terminal. It stops short of describing permissions or pagination edge behavior.

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 returned fields and sort order come first, then queryable filters, then limitations and the create-refund exclusion. Every sentence carries distinct information; nothing is padded.

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 returned fields and sort order, and it covers filtering, limitations, and the create-refund exclusion. Combined with complete schema coverage and annotations, an agent has everything needed to call it correctly.

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 page, pageSize, search, and orderId are already documented in the schema. The description largely restates these (order-id filter, refund receipt search) and adds only the mild clarification that the search targets the REFUND's own receipt number rather than the order's. Baseline 3 is appropriate.

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 ('Refunds recorded against orders, newest first') and enumerates the returned dimensions (what, why, by whom, which order, which customer). It clearly separates itself from sibling reads like hub_get_sales_breakdown, hub_get_financial_summary, and hub_get_order.

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 concrete user questions it answers, names both supported filters (order id, refund's own receipt number), and explicitly routes the date-range case to get_sales_breakdown or get_financial_summary. It also states the exclusion that refunds cannot be created here, pointing to the POS terminal instead.

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