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

Annotations declare destructiveHint=false and idempotentHint=false, and the description goes beyond that by spelling out the state effects (payment unlinked, row back to its earlier review, balance moves back) and implying re-linking is possible afterwards. It also adds a communication obligation ("Say so to the person"), which is behavior an agent cannot infer from the schema. It does not say whether the unlinked payment becomes unapplied cash or what is returned.

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 is front-loaded in the first clause and the whole thing is under ~50 words. The fragment "Say so to the person" and the "Effects:" recap are slightly clipped in style, but every line carries information.

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 3-parameter mutation with no output schema and coverage-rich annotations, the description covers purpose, trigger conditions, and state effects. The remaining gap is what happens to the unlinked payment downstream (unapplied cash / reconciliation) and what the call returns.

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%, so loan_id and payment_id are already documented. The description adds only that the unlink is done "with a reason", signalling that reason is mandatory and substantive, but gives no guidance on what a good reason contains beyond the schema's terse "Why."

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 payment link" gives a specific verb + resource and immediately states the effect (row returns to its earlier review, balance moves back). It is unambiguous against the sibling set, though it never names its counterpart loan_link_payment 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?

"For a link that was wrong, or to relink it with the lender's split once the statement arrives" gives two concrete situations that select this tool. It stops short of naming when-not-to-use or pointing at a specific alternative tool.

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