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

Annotations provide only readOnlyHint=false, so the description carries most of the burden. It adds the meaningful eligibility constraint (who may propose, on which task states) beyond the annotation, but says nothing about the proposal lifecycle, reversibility, or what happens on acceptance/rejection.

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 tightly packed sentences: the mechanism first, then the eligibility rule. No filler, and the operative constraint is front-loaded.

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 need no explanation, and the schema fully covers parameters. The description covers purpose and eligibility; the only gap is the post-proposal flow, which is arguably handled by respond_settlement.

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%, so the schema already documents id, note, refund_pct, and buyer_token in detail. The description's restatement of the refund_pct split is redundant with the schema field text, adding no syntax or format information beyond it. Baseline 3 is appropriate.

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 (offer a partial refund) with the exact split mechanics: refund_pct goes to the buyer, the seller keeps the remainder. It does not name the sibling respond_settlement, so the distinction from the counterpart tool must be inferred, but the action itself 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?

Explicitly states who may call it and in what situation: the buyer on a delivered task, or either side on a disputed one. This is real eligibility guidance, though it never names respond_settlement as the alternative path once a proposal exists.

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