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

Goes well beyond the annotations: discloses per-call pricing ($0.01 USDC on Solana via x402), the exact MCP payment handshake (call without payment, receive PaymentRequired, retry with _meta["x402/payment"]), the HTTP equivalent endpoint, and the coverage-flag behavior for uncovered batch members. The annotations only mark readOnly=false and idempotent=false; the description explains why the flow behaves as it does.

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-loads what the tool returns, then input modes, then preflight and payment mechanics. Dense but every clause carries operational value; only slight compression possible in the payment retry explanation.

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?

No output schema exists, yet the description conveys the return shape (per-snapshot series plus two delta comparisons and coverage flags) and complete payment/preflight mechanics. Remaining gap is NDC format and the single-vs-batch mutual requirement.

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 0%, so the description must compensate. It explains the ndc vs ndcs alternatives and the max-25 batch semantics with covered:false marking, but omits NDC string format and does not clarify that at least one of the two zero-required parameters must be supplied.

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?

States the specific resource and shape: per-NDC per-unit NADAC values across every held snapshot generation, plus latest-vs-previous and latest-vs-12-month-anchor deltas. This implicitly distinguishes it from point-in-time siblings such as nadac_fact and dispersion tools, though it never names them.

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?

Gives concrete input modes (single ndc or ndcs batch up to 25) and points to a free preflight endpoint, which is useful routing. However, it never says when to choose this over nadac_fact or nadac_dispersion, and gives no exclusion guidance.

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