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

The description adds important behavioral detail beyond the annotations: it enforces a hard limit with 'Refuses more than is still held' and clarifies an external side-effect boundary with 'The invoice server is not touched: a refund is not a payment.' These are exactly the kind of constraints an agent needs to know.

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?

Three short sentences deliver the purpose first, then the key constraint and the external-boundary clarification. There is no filler, and every sentence contributes to correct tool selection and invocation.

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?

For a mutation tool with no output schema, the description is complete: it covers partial/full refunds, over-refund refusal, recording date and method, and isolation from the invoice server. An agent has enough context to decide when to call it and what to expect.

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 the parameters are already well documented. The description mentions 'part or all' and 'the date and how it was sent,' which aligns with amount_minor, date, and method, but it adds no new parameter semantics beyond the schema.

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 the specific operation—'Give part or all of a held deposit back to the client'—with a clear resource and scope. It distinguishes the tool from payment-related actions by noting 'a refund is not a payment,' which helps separate it from deposit_apply and invoice concepts.

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 clearly implies the core use case: returning money from a held deposit. However, it does not explicitly name sibling alternatives or state when not to use this tool. The 'not a payment' caveat hints at boundaries, but the guidance is implied rather than explicit.

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