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

Annotations only declare readOnlyHint=false, so the description carries the burden of behavioral disclosure. It clearly states that this call changes stored state, is not safe to repeat blindly, creates no liability, moves no money, and joins existing evidence. It also discloses the one-binding-per-receipt constraint. This is strong behavioral context beyond the annotation.

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 description is dense but every sentence earns its place: the gap, the consequence, the caller restriction, the no-money/no-liability behavior, and the write warning. It is front-loaded with the core purpose. Slightly long, but justified by the need to explain an unusual edge-case tool.

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 two-parameter tool with no output schema, the description covers the trigger condition, caller authorization, side effects, and failure mode. It doesn't describe the return value, but with no output schema and a simple award_id/secret input, the missing return format is a minor gap. The write warning and refusal condition make it complete enough for correct invocation.

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%, so the description must compensate. It explains the purpose of award_id contextually (the award to close) and mentions secret only implicitly through the caller restriction. It doesn't add explicit detail about the secret parameter, but the schema already names it and the description's caller guidance helps infer its role. Baseline 3 is appropriate because the description adds some meaning but doesn't fully document both parameters.

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?

The description states a specific verb and resource ('Close an award against a payment that was ALREADY recorded') and clearly distinguishes this from the normal settlement path inside the receipt write. It also names the exact gap it fills, so an agent can tell it apart from siblings like mark_award_payable or payout_binding without opening schemas.

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?

It explicitly explains when to use this tool: when a receipt was recorded before an award was decided, leaving an award still reading payable. It also states who may call it (payee or funder) and what it refuses to do when there is no recorded payment, giving clear context and an implicit exclusion of the normal receipt-write path.

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