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

Goes well beyond the annotations by disclosing the required scope, the fact that this tool itself does not move money (the refund happens only when the recipient opens the URL and signs in), the side effect that re-calling invalidates the previous link, and the handling instruction not to open or forward the URL. The replacement semantics are consistent with idempotentHint=false, and no claim conflicts with the readOnly/destructive hints.

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?

Purpose and permission requirement are front-loaded, and each subsequent sentence contributes either side-effect information or handling instructions. A few phrasings are awkward ('Answers a link for the person to open'), but nothing is truly wasted.

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 one-parameter tool with no output schema, the description covers the important ground: what comes back (a URL), who consumes it, permission requirements, link-replacement behavior, and how to verify usage. It omits link expiry or failure modes, which would round it out fully.

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 single `payment_id` parameter has 0% schema description coverage, so the description must carry the meaning. Saying 'a payment I received' implicitly narrows it to received payments (consistent with the get_received_payment/list_received_payments siblings), but it never names the parameter or states its expected format, so the added value is partial.

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 concrete verb and resource ('Get a link to refund a payment I received'), which clearly separates it from paylink creation tools. It does not explicitly contrast itself with the many other link-getting siblings (get_paylink, get_checkout_link, get_cancel_link), so the agent must infer the boundary, but the resource type ('refund a payment I received') is specific enough to route correctly.

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 clear operating context: requires `payments:write`, the link is for the payer to open themselves, and calling again replaces the prior link. It also points to `get_link` for checking usage status, which is useful follow-up guidance. It stops short of explicit exclusion criteria (e.g. when to prefer get_paylink or revoke_link), keeping it below a 5.

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