list_refunds

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

There are no annotations provided, so the description must carry the burden of behavioral disclosure. It says the tool lists refunds (a read operation) and optionally filters by booking, which implies a safe query. However, it does not mention pagination behavior (max_items), ordering, or what fields the returned refunds contain. The output schema exists but is not shown, so the description adds minimal behavioral context beyond the basic read operation.

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 a single concise sentence that is easy to parse. It front-loads the primary action and resource, with the optional modifier appended. No wasted words, though it barely earns its place given the lack of parameter and usage detail.

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?

Given the tool has an output schema (which handles return values) and two simple optional parameters, the description is thin. It does not cover the max_items pagination parameter, which is a common need, nor does it clarify the relationship to list_payments for refund-specific queries. The context of guest refunds vs. property payments is left undefined, so an agent may under-specify calls.

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 0%, meaning the description does not explain any parameters. The input schema includes max_items (with default 100) and booking_id (nullable), but the description only hints at the booking filter. The max_items parameter is completely undocumented, and no parameter semantics are added beyond what the schema's name and type imply.

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 states a clear verb ('List') and resource ('guest refunds') and notes an optional filter ('optionally for a single booking'). It is specific enough to distinguish from siblings like list_payments or list_bookings, though it could more explicitly contrast with list_payments since refunds are a subset of payments.

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?

The description implies a default use case (listing all refunds) and an alternative (filter by booking_id), but it does not explain when to use this tool versus list_payments or other financial tools. No explicit exclusions or prerequisites are stated, leaving some ambiguity for an agent deciding between refunds and payments.

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