Verification Oracle (paid, credits or x402)

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

Annotations already declare read-only/idempotent/non-destructive, and the description adds valuable behavior beyond that: cost ($0.15 USDC, x402, free tier), latency range, output structure, and the meaning of 'abstain'. This is rich, non-redundant context that helps the agent anticipate side effects and results.

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 long but tightly organized with labeled sections (WHAT, WHEN, WHEN NOT, COST, LATENCY, OUTPUT). Every sentence provides distinct and necessary information, and the most critical what-it-does is front-loaded. No filler or 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 2 params, no schema descriptions, and an output schema, the description covers purpose, usage conditions, exclusions, cost, latency, output structure, and the abstain semantics. It addresses both selection and invocation contexts comprehensively, leaving very little to infer.

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?

Input schema has zero description coverage, and the description does not explain the structure of the `job` or `spec` objects. It mentions three job domains but not how to encode them, leaving parameter usage ambiguous. The description compensates only partially; an agent would still need examples or field-level semantics to invoke correctly.

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 'WHAT: independently checks another agent's work' and enumerates specific domains (citation support, code correctness, dataset/schema conformance). It clearly distinguishes a verification oracle from sibling research/report/spend/judge tools, and it specifies the unique output (verdict + signed attestation).

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?

The 'WHEN' section lists concrete scenarios (before paying for subcontracted work, before merging agent-produced content) and 'WHEN NOT' gives explicit exclusions (already trusted work, subjective judgments, non-Python code). This provides strong guidance on when to choose this tool over alternatives.

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