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

Annotations already declare a non-destructive, closed-world mutation, so the bar is lower. The description earns credit above annotations by disclosing a one-use, ten-minute confirmation and the non-mutating outcome, but says nothing about what happens when the confirmation expires, is reused, or the expected version is stale.

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?

Two short sentences with zero filler, and the non-mutation boundary is placed last for emphasis. Efficient, though the extreme terseness is part of why the parameter and expiry gaps exist.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. However, for a 7-parameter preparation step with 0% schema coverage, the definition leaves too much of the calling contract and the confirm-then-record workflow unstated.

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 0% across 7 parameters, so the description carries the full burden and adds almost nothing: no mention of idempotencyKey, expectedVersion, paymentMethod, paymentProofId, or paymentReference semantics. Only a faint implication that the invoice is identified and version-checked.

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 specific actions: shows the exact unpaid invoice and records a one-use ten-minute confirmation. The negation "does not mark the invoice paid" sets it apart from the mutating sibling (record_invoice_payment) without naming it, so an agent can distinguish the two, though the negative framing rather than a positive workflow statement leaves a little inference.

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?

Implies the workflow by saying the invoice is not marked paid, which steers an agent to a follow-up payment-recording tool, but it never names that alternative or states prerequisites such as which invoice states qualify. Usage is inferable rather than explicit.

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