nayori_appeal_decision

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

The annotations (readOnlyHint false, destructiveHint false) are supplemented with rich detail: it moves no funds, costs no extra service fee, marks the job disputed, describes the resolution outcome, notes that only the SHA-256 of appealReference goes on-chain, and clarifies that a returned txid is not confirmation. This goes far beyond the annotations and provides critical side-effect information.

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 single paragraph but well-structured: it states the purpose first, then conditions, effects, and return behavior. Every sentence adds value, though it is somewhat lengthy. It remains appropriately detailed for a complex write operation without redundancy.

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?

Given the tool's complexity (write operation with conditions, side effects, and no output schema), the description covers the key aspects: who can appeal, what happens, what goes on-chain, and the meaning of the return value. It does not mention potential error conditions or explicit prerequisites beyond the deadline, but overall it is sufficient for correct invocation.

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 only 33% (only appealReference has a description). The description adds meaningful context for appealReference (evidence URL/CID, only its hash goes on-chain) but does not elaborate on asset or jobId. While those parameters are self-explanatory via schema (enum and integer range), the description does not fully compensate for the low coverage.

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 opens with 'WRITE (mainnet). Appeal the Evaluator's recorded decision on a job', clearly stating the action, resource, and context. It distinguishes this from sibling tools by focusing on the appeal process, which is unique among the listed operations (apply, submit, etc.).

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 specifies when to use it: the CLIENT can appeal an approval and the PROVIDER can appeal a rejection, once, until the on-chain deadline. This gives clear conditions for use without naming alternative tools, but the conditions are sufficient for an agent to decide when to invoke it. It does not explicitly say 'when not to use' but the constraints imply it.

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