Signed verdict for an action (paid)

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

Annotations only say readOnlyHint and openWorldHint, but the description adds material behavior: the call costs $0.01 via x402/USDC on Base, requires KYA_PRIVATE_KEY to be set, and returns a signed verdict enumerating every evaluated rule that can be used as dispute evidence. None of that is recoverable from the annotations or schema, so the description carries real added value.

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?

Three tight sentences, each doing distinct work: pricing/auth, the decision being made, then the fallback sibling. The only weakness is that the dense parenthetical '$0.01 (x402, USDC on Base; set KYA_PRIVATE_KEY)' puts implementation jargon ahead of the purpose statement, so the tool's job is not the very first thing read.

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?

With 8 parameters, no output schema and no destructive/denial semantics in the annotations, the description does the essential work: it explains the payment barrier, the credential prerequisite, and the shape of the returned verdict. It stops short of explaining failure/denial behavior or error responses, which would be useful for a paid, decision-returning call.

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%, and each parameter (action, amount, spent_today, counterparty, payment_ref_sha256, etc.) already has a clear schema description, including the note that spent_today is needed for max_per_day because the issuer keeps no record of acts. The prose references actions, mandates and credentials conceptually but adds no syntax, format or constraint detail beyond the schema, 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 states a precise verb+resource: decide whether an agent may perform a given action under its mandate and whether its credential is currently active. It also distinguishes itself from the sibling kya_check_mandate by delivering a signed, evidentiary verdict rather than a free unsigned answer, so an agent can route between them without opening either schema.

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 gives an explicit when-to-use rule ('For a free, unsigned answer use kya_check_mandate on the mandate from kya_verify'), which both names the alternative and states the condition that selects it. The paid nature of this tool is stated up front, which is the key selection criterion against its free sibling.

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