verify

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

No annotations are provided, so the description carries the full burden. It discloses the sealed sandbox, determinism requirement, synchronous verdicts with detailed meanings (BROKE, HELD, FINDINGS, DROP), and payment terms (0.10 USDC, x402 v2 on Base, charged for every delivered verdict, cancellation if no verdict). This is exceptionally transparent.

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 it is tightly organized and front-loaded with purpose, then usage, inputs, verdicts, and payment. Every sentence carries operational or conceptual weight, and the uppercase verdict labels make the length navigable.

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 tool with no annotations and no output schema, this description is complete enough to select and invoke correctly: it covers input requirements, verdict semantics, consequence directions, and payment failure behavior. The only minor gap is the exact response shape for verdicts, but the behavioral descriptions of BROKE/HELD/FINDINGS/DROP provide enough for safe usage.

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 already 100%, but the description adds critical semantics: code must be JavaScript/Node or Python 3 and deterministic, exactly one of contract vs assumption should be supplied, contract pairs must be copied from the test/spec, and assumption is a weaker plain-language read that can only trigger FINDINGS, never BROKE. This goes well beyond the schema's property names.

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 defines verify as 'an outside check on code, executed in a sealed sandbox' and immediately gives concrete trigger scenarios (merge, deploy, publish, settle, report done). This is a specific verb-plus-resource statement with clear scope, and it explicitly contrasts itself with a self-audit, making the purpose unambiguous even without sibling tools.

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 explicit when-to-use guidance: before any consequence boundary (merge, deploy, publish, settlement, done report), and in the specific case where a fix passes your own check but the target still fails. It also sets a boundary by requiring deterministic code and explaining what the tool cannot do ('never completeness'), which functions as a when-not.

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