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

Annotations already declare non-readonly, idempotent, non-destructive behavior, so the safety bar is covered. The description adds genuine consequence context beyond that: refunds stop maker payouts and preserve other buyer liabilities, telling the agent the downstream effects of its decision. It still omits auth/permission requirements.

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, zero waste, with the action front-loaded and the consequence following. Nothing is padding.

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 mutation tool with no output schema, annotations cover the safety profile and the description covers consequences, but the parameter layer is entirely bare and there is no guidance on prerequisites or relationship to the refund-requests listing. Adequate but with clear gaps.

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% and the description never mentions any of the four parameters. accept is self-evident from its name, but request_id, order_id, and agent_key are completely undocumented in both the schema and the description, so the description does not compensate for the coverage gap.

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 (accept or decline) and resource (buyer refund issue), which lets an agent distinguish this adjudication action from the read-only sibling speedbot_product_refund_requests. It does not name a sibling explicitly, but the decision verb is unambiguous.

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?

Usage is implied: an agent will infer this applies to a pending refund request it has already fetched. There is no explicit when-to-use guidance, no prerequisites (e.g. required role or that the request must exist), and no mention of the related listing tool.

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