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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered; the description goes further by naming the concrete consequences ("refund unlinked; the row back to its earlier review", "the purchase counts in full again"). The instruction "Say so to the person" also hints the agent should surface the change to the user, which is behavior beyond the annotations.

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 core action is front-loaded, but the same consequence is restated twice ("The money-in row goes back to how it was reviewed before" vs. "the money in goes back to how it was reviewed"), and "Say so to the person" is an unexplained instruction that muddies rather than clarifies.

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 destructive two-parameter mutation with no output schema, the description covers the important thing an agent needs: what state is restored and that the purchase is re-counted in full. It omits error/edge behavior (nonexistent or already-unlinked refund) and permission requirements, but the essential call semantics are present.

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 coverage is 100% and both parameters (refund_id, reason) are documented in the schema, so the baseline of 3 applies. The phrase "with a reason" echoes the required reason parameter but adds no format, length, or content guidance beyond "Why it was wrong."

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?

"Undo a refund link, with a reason" gives a specific verb (undo/unlink) and resource (refund link), which cleanly inverts the sibling purch_link_refund. An agent can distinguish it from purch_unlink_reimbursement/purch_unpair_transfer by the resource alone, though the description never names those siblings explicitly.

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?

Usage is implied by "For a link that was wrong" and "Undo a refund link," which gives a clear trigger condition. However, it names no alternatives (e.g. purch_link_refund, purch_unlink_reimbursement) and states no exclusions or prerequisites, so the agent must infer the routing.

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