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

With no annotations, the description carries the full burden and does so well: it discloses the underlying method (BFS to nearest OFAC/hack/mixer root), the full class enum, the semantics of 'unknown' as truncated/unloaded rather than a false 'none', and that no auth is required. It omits performance/rate-limit behavior, which keeps it from 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?

Three sentences, front-loaded with the tool's operation and output before caveats. Dense but every clause earns its place; only the §8 reference is unexplained overhead.

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 must describe return values, and it does (class, nearest-hop, haircut fraction, plus the chain_id/chain_source/chains_with_data fields). Combined with no annotations, this is nearly complete, though a note on how to interpret the haircut fraction or handle tainted-but-truncated results would close the gap.

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 description coverage is 100%, so the schema already documents both the chain and address parameters in depth. The description adds no syntax or format detail beyond the schema, so this sits at the baseline 3.

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 states a specific verb+resource ('bounded backward BFS over the value graph') and names the exact output ('class, nearest-hop, and a value-proportional haircut fraction'), so the agent knows precisely what it gets. It does not, however, differentiate itself from close siblings like get_address_compliance, get_address_risk, or get_sanctions_status, which an agent could easily confuse it with.

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?

It provides a meaningful caveat ('Heuristic risk signal, not an AML/legal determination') and an in-flight guidance note ('read it before concluding, then ask again with chain set'), which implies usage. But it never states when to prefer this over get_address_compliance/get_address_risk or what alternatives exist, so routing remains largely inferred.

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