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

Annotations already declare idempotentHint=true and openWorldHint=false, so the 'Idempotent for the same evaluation' line reinforces rather than adds. The genuine additions are the workflow gate ('never call this before settlement') and the handling warning that the reservation token is private — neither is inferable from 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?

Three short sentences, front-loaded with the effect, then prerequisites, then the hard prohibition. No filler and no repeated annotation boilerplate.

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 three-required-param mutation with a full output schema and full annotation coverage, the description supplies everything an agent needs to sequence the call correctly: prerequisites, the ordering constraint, and token confidentiality. Return values are legitimately left to the output schema.

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 the baseline is 3; the description earns a bump because it names the producing tool (evaluate_payment) for evaluation_id and reservation_token, which the schema only describes generically as 'returned by an ALLOW verdict.' It otherwise restates the schema's own definitions of settlement_ref.

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 effect: confirm that an ALLOWed payment settled. The conditional 'ALLOWed' distinguishes it from evaluate_payment (which produces the verdict) and from release_evaluation, so an agent can tell what stage of the lifecycle this tool occupies without opening the 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 a clear precondition chain (must have an evaluation_id and reservation_token returned by evaluate_payment) plus an explicit exclusion: 'never call this before settlement.' What it doesn't say is what to do when the payment did not settle, i.e. whether to release the reservation — no routing for the failure branch.

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