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

Goes well beyond the annotations by disclosing the two operating modes (offline preview unless PAYGUARD_X402_PRIVATE_KEY is set), the exact payment mechanism and cost ($0.001 USDC on Base per address over x402), and the remote endpoint. For a tool that can incur a real monetary charge, this is exactly the behavioral context the agent needs and could not get from readOnlyHint/idempotentHint.

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 the core purpose, then the free/paid behavior, then the required env var, then the disclaimer — a sensible priority order. Dense but each sentence carries information; the URL and per-address price could arguably be compressed, but nothing is filler.

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 usefully sketches both return shapes (sanctioned boolean, match count, chain guess in preview; SDN entity, programs, list date, checksum in the paid tier). The one meaningful omission is the relationship to the batch sibling screen_addresses, which matters for a single-address tool.

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 the baseline is 3, but the description adds genuine meaning by naming the accepted address families (EVM, BTC, TRX, SOL, LTC, XMR and more), which the bare "Blockchain address" schema text does not convey. It stops short of giving format/validation details such as checksum or case requirements.

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 verb and resource with scope ("Reports whether a crypto address ... appears in the US Treasury OFAC SDN list") and enumerates supported chains, so the operation is unmistakable. It never mentions the sibling screen_addresses, so an agent cannot tell from the description alone whether this is the single-address or batch variant.

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 implies usage context via the free-preview-by-default vs. paid-full-result split, and adds the caveat "Informational screening, not legal advice." However, it gives no explicit when-to-use/when-not guidance and does not route the agent between this tool and screen_addresses, leaving the alternative undisclosed.

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

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, closed-world), and the description adds pricing context not present in structured fields ($0.01 USDC per batch, paid endpoint URL). However, it introduces "paid mode" without explaining what the non-paid mode is, whether payment is required, or how failure/refund behaves — leaving a real ambiguity around cost behavior.

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?

Two short sentences, front-loaded with the batching scope and then the cost detail; nothing is redundant. The opening "Same screen" is too terse to be self-contained, which keeps it from a 5.

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 and minimal annotations, the description should clarify address format, free-vs-paid mode semantics, and what comes back (matches, risk scores, per-address results). It covers cost and batch size but leaves those gaps, so it is only adequate for a single-parameter screening tool.

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?

There is one parameter with 0% schema description coverage, so the description must carry the semantics. It confirms the 50-address cap (already encoded as maxItems) but says nothing about required address format — hex, chain-specific, checksummed, etc. — which is critical for a screening call.

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 opens with "Same screen," which only identifies the operation by reference to the sibling screen_address rather than stating the verb and resource itself. "For up to 50 addresses in one call" does differentiate it as the batch variant, but an agent must consult the title or sibling to learn that this is an OFAC SDN screen.

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?

"in one call" hints that this is the batch option, but the description never explicitly says to use this instead of screen_address when multiple addresses are needed, nor when not to use it. There is no guidance about prerequisites, free vs paid mode selection, or failure handling for oversized inputs.

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