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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety and repeat-call behavior are covered. The description adds genuinely non-structured context: the elevated authorization model (admin key plus wildcard scope, owner status insufficient) and that provider receipt, currency and amount are validated before bookkeeping. It does not describe failure behavior when verification fails, which is the remaining gap.

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 tight sentences with zero filler: what it records first, who may call it second, what it validates third, and what it does not create last. Every clause carries information an agent needs.

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?

With an output schema present, return values need no explanation, and the description covers identity, authorization, validation and scope adequately for a mutable bookkeeping tool. The only shortfall is the absence of any note on behavior when provider verification fails or when a duplicate adjustment is attempted, which the idempotency annotation only partly covers.

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 every parameter including lineId, amountCents sign convention and the credit-note/debit-invoice conditionals is already documented. The description's 'Verifies exact provider receipt, currency and amount' adds only a light hint about validation, and notably references currency that is not a parameter, so it does not materially extend parameter meaning beyond the schema. Baseline 3 applies.

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 specific verb and resource ('Record an already-issued provider credit note or debit invoice against an existing agency billing line') and immediately draws the boundary against adjacent capabilities with 'Creates no invoice, payment or subscription.' An agent can distinguish this from the billing-configuration siblings without opening any schema.

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 preconditions ('Platform finance operators only: requires the existing admin key and wildcard scope; agency owner status is insufficient') and implies the correct context is correcting an existing line rather than creating one. It stops short of naming an alternative tool for related billing operations, so it is clear context without explicit when-not routing.

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