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

With no annotations present, the description carries the full burden and does so well: it discloses transliteration of non-Latin names, that unscreenable names return HTTP 400 rather than a false clear, the per-call price, the payment rail (USDC on eip155:8453 via x402), and the endpoint. Missing only rate limits and any note on idempotency/partial-batch failure, so not a 5.

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?

Dense and front-loaded: covered lists first, then capabilities, then failure mode, then price/endpoint. Every sentence adds something, though the capability enumeration could be trimmed to remove the sibling-overlap confusion, and the HTTP URL at the tail is of marginal use to an agent.

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, so the description is the only place to explain what a batch screening returns – yet it says nothing about per-name match results, threshold scoring output, or how a 400 for one bad name affects the rest of the batch. For a 3-parameter paid batch tool with zero annotations, that leaves a meaningful gap despite the strong cost and failure disclosures.

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 a 3 is the baseline for days/names/threshold. The description earns above baseline by documenting the payment parameter params._meta["x402/payment"], which the schema does not expose at all, plus the 'up to 50' batch limit that complements the names parameter's schema text.

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 names the verb (screening), the covered lists (OFAC, OFSI, EU), and enumerates modes, so the resource is clear. But it does not distinguish this tool from siblings like check_sanctions__screen, check_sanctions__address, and check_sanctions__watchlist – it actually lists capabilities ('a name, a wallet address, a batch, or your own watchlist') that those siblings appear to own, blurring the boundary instead of sharpening it. The name implies 'batch' but the prose does not state that batch semantics (up to 50 names) are its differentiator.

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?

There is no statement of when to prefer this over check_sanctions__screen or check_sanctions__address, nor any exclusion criteria. By claiming it can screen a single name, a wallet, or a watchlist, it arguably competes with its siblings rather than pointing to them, which leaves selection entirely to inference from the tool name.

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