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

With no annotations, the description carries the full burden and does so well: it discloses consequences (on-time payment removes the entry and counts a completed dealing; late payment lifts most weight but keeps the lateness), that silence never confirms, that on-chain verification does not run for these orders, and the credential/cost. This is meaningful behavioral context beyond the schema.

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?

The description is a long, dense block of legalese with parenthetical citations (PD14 §9, §10; Dealings Act 4.8A) interspersed throughout. It is not front-loaded and forces the reader to reconstruct the action and workflow from declarative fragments, rather than leading with what the tool does.

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 complex, multi-party refund-satisfaction tool with no output schema, the description covers the key elements an agent needs: who may call, the alternative rail, the effect on the record, the timing rule, and that only the buyer or Registrar confirms. It is complete on substance even if hard to read.

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 83%, so the schema already documents most parameters, and the description's parameter context (paidBy: provider, buyer confirms receipt, 'text alone is not proof') largely echoes the schema descriptions. It adds little format or syntax detail beyond what the schema provides, so the 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?

The description conveys that this tool records/lodges a refund payment state and lets the buyer confirm or dispute it, but it opens with declarative conditions ('The publisher has paid the buyer back, or I am the buyer and the money arrived') rather than a clear verb+resource, so an agent must parse several sentences before knowing it is a write/confirm action. It does name the sibling publisher_pay as the alternative rail, which helps differentiate it.

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?

It explicitly routes the agent: a verified publisher lodges under its own key with publisher_pay instead, while the supplier agent or Registrar lodge here with paidBy: provider. Roles for who may call (buyer confirms, Registrar confirms on evidence) are stated, though the when/when-not is embedded in dense prose rather than cleanly signposted.

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