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

Adds real behavior beyond annotations: required scope recover_payments, the fact that it enqueues rather than delivers synchronously, and the specific failure code for review-pending payments. Annotations cover safety/idempotency, but the description does not explain why destructiveHint is true (i.e., that a retry actually moves money), leaving that risk implicit.

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?

Four short sentences, every one carrying distinct information: action, precondition, permission, async semantics, follow-up, and refusal case. Front-loaded with the action, 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?

For a two-parameter mutation with no output schema, it covers prerequisites, permission requirement, async behavior, how to verify the result, and the known error path. Nothing further is needed to call it correctly.

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%, including the applicationId defaulting rules and the purchases[].id source, so the schema does the heavy lifting. The description only indirectly adds selection criteria via 'paid but not delivered' and 'reviewReason', which roughly maps to filtering purchaseId; 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 ('Queue one Tribute payment for delivery again') plus the qualifying scope ('a payment that was paid but not delivered'). An agent can immediately distinguish this from list_tribute_purchases, which is named as the read-side counterpart.

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 (paid but not delivered), a post-call step (read list_tribute_purchases afterwards), and an explicit refusal condition (TRIBUTE_REVIEW_REQUIRED when a reviewReason exists). It does not name an alternative tool for the review-blocked case, which is the only gap.

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