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 the authorization model, the in-transaction verification, that no financial transfer or settlement ever occurs, and idempotency keyed on idempotencyRef. It omits failure behavior (what an agent sees on rejected proof, expired authorization, or already-resolved dispute) and any sense of the response shape.

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 tight sentences, front-loaded with the action and outcome, then prerequisites, then the safety-relevant negative claim about financial transfers. No filler or restatement of the title.

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 six-parameter, authorization-gated mutation with no annotations and no output schema, the description covers the operation, authority requirements, outcome space, and idempotency. The remaining gap is the return value, which with no output schema is left entirely to inference.

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%, so the schema already documents all six parameters including the outcome enum. The description restates the outcome values (redundant with the enum) and adds only modest meaning by tying idempotency semantics to idempotencyRef; it says nothing extra about proof structure, reason, or agentId binding beyond what the schema notes.

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 precise verb+resource+effect: records an evaluator decision on an open dispute and transitions the commitment to one of four canonical nonfinancial outcomes. This is clearly separable from siblings like raise_dispute (which opens) and list_disputes (which reads), and the named outcome enum pins down what 'resolve' means here.

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 explicit preconditions for use: the dispute must be open, the caller must supply an EIP-712 authority proof, and must hold an unrevoked, unexpired EVALUATOR authorization verified in-transaction. It stops short of naming alternatives or stating when-not to call it (e.g. what to do if authorization is missing, or which sibling to use to check authority first).

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