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

Goes well beyond annotations: discloses pay-per-call cost ($0.02 USDC on Solana via x402), the MCP payment dance (call unpaid to get PaymentRequired, then retry with _meta["x402/payment"]), a free preflight endpoint, and the HTTP equivalent URL. Also discloses that absent brand/generic sides yield 'honest nulls'. Annotations only flag readOnlyHint=false and openWorldHint=true, so this added context is substantive.

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 computes before the payment/logistics detail, and every sentence carries information (output shape, preflight, x402 flow, HTTP fallback). The payment instructions are dense but functional; nothing is redundant.

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 no output schema, the description still describes the return payload (presentations list plus stats object and brand/generic comparison), and it fully covers the access/payment path an agent must follow to invoke it successfully. Nothing material is missing for correct invocation.

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% and the single 'ndc' param is undocumented in the schema, but the description compensates by explaining the matching key: the NDC resolves to an exact ndc_description against which dispersion is computed. That adds real semantics, though the expected NDC format (11-digit? hyphens?) is never specified.

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 a specific operation (dispersion metrics across presentations sharing the input NDC's exact ndc_description) and enumerates the outputs (count/min/max/median/mean, brand-vs-generic medians and gap). It is distinguishable from siblings like nadac_fact and nadac_changes, though it never names those siblings explicitly.

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?

Mentions a free pre-check at /toll/nadac/dispersion/preflight but gives no explicit guidance on when to prefer this tool over nadac_fact or nadac_changes, or when the preflight is required versus optional. Usage is implied by the pricing/payment flow rather than stated as a use criterion.

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