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

With no annotations, the description carries the full burden and does well: it discloses cost ('FREE'), the exact matching rule (EVM 0x case-insensitive, all others exact), what a hit returns, and a legal-use caveat. Gaps remain on list freshness and whether results are cached or rate-limited, which matters for a compliance-screening tool.

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?

Four tight sentences, front-loaded with 'FREE.' and then the core action, with the caveat last. Every clause carries information an agent needs: coverage, matching rule, return shape, disclaimer.

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?

There is no output schema, and the description compensates by describing the response (match/no match plus SDN name, UID, programs, list date, source). For a one-parameter lookup tool, nothing needed to call it correctly is missing.

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% for the single 'address' parameter, so the baseline would be 3, but the description adds real semantic value by stating that EVM 0x addresses match case-insensitively while other chains must match exactly. That normalization rule is not in the schema and directly affects whether a caller's input will match.

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 (screen) and resource (one crypto wallet address) against a named dataset (OFAC SDN 'Digital Currency Address' entries) with the covered chains enumerated. The word 'one' plus the named dataset cleanly separates it from crypto_address_batch_check and batch_screen without the agent opening either schema.

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?

'Screen one crypto wallet address' implicitly scopes this to single-address lookups, which routes against the batch siblings, and 'FREE' signals there is no cost barrier to calling it. It stops short of explicitly naming when to prefer crypto_address_batch_check, and the 'screening aid only, not legal or compliance advice' line sets expectations without stating any precondition for use.

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