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

Annotations only declare the generic profile (not read-only, open-world, not idempotent, not destructive). The description adds concrete facts the annotations cannot convey: the exact price (0.05 USDC on Base, eip155:8453), that each call is billed individually, where settlement appears (result._meta['x402/payment-response']), and the important refund rule that failed calls are never charged. It stops short of describing the review payload itself.

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?

Front-loaded with what the tool does, then the cost and payment mechanics, then the failure-billing rule and HTTP alternative. Dense with protocol jargon but every sentence carries operational information; a light edit could tighten 'One call, one review.' which partly restates the per-call pricing.

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 paid tool with no output schema and non-idempotent billing, the description covers the things an agent must know to avoid double-charging: the price, the two-step payment handshake, where the receipt lands, and that failed calls are free. The only gap is the shape of the review result, which is secondary to getting the payment flow right.

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 ask, code, diff and lang are already documented, and the description adds nothing about their semantics (e.g. code vs diff precedence). It does add one genuinely new parameter concept absent from the schema: params._meta['x402/payment'] as the carrier for the signed payment. That is useful but narrow, so the baseline of 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?

Names a specific resource and mode: 'Verse code review, closer read: the instant checks plus an AI reviewer that confirms real findings, drops wrong ones and adds what patterns miss.' That distinguishes it from a plain instant-check reviewer. However, it never names the siblings it overlaps with (review_code, review_code_closer) or explains how it differs from them, so an agent must infer the routing.

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 description gives strong procedural guidance for the payment handshake (call unpaid to receive PaymentRequired, then retry with the signed payload) and points to an equivalent HTTP endpoint. It gives no guidance on when to choose this over review_code_closer or review_code, which is the more important selection question given three review siblings.

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