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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds value beyond them by disclosing the 72-hour rejection rule and clarifying 'This does not move sats or cash', but it stays silent on the non-idempotent behavior (duplicate claims on retry), which is the main residual risk.

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, purpose front-loaded, then conditional usage, then constraint. Every sentence earns its place with zero filler.

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 needn't be explained, and annotations cover the safety profile. The description supplies the key operational constraints (72h limit, non-financial outcome, basket handling), leaving only idempotency/retry behavior 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 100% and the descriptions already explain line/sku as the multi-line selectors, so the description's 'pass line or sku' largely restates the schema. Baseline 3 is appropriate since the schema carries the parameter semantics.

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 action (request a service-credit review) on a specific resource (one paid call), and the name plus description together distinguish it from sibling tools like report_outcome and report_sku. An agent can immediately tell what the tool does 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 concrete usage context: 'For a basket, pass line or sku' and the 72-hour eligibility window. It clarifies the multi-line case well but never names an alternative sibling or states when NOT to use this tool, so it stops short of explicit routing.

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