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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description's real addition is the cost asymmetry — 5 API units on EVM versus 1, because tracing hits paid indexers — which is genuine behavioural context an agent budgeting calls needs. It stops short of describing result shape or what an empty cluster set means, though an output schema exists.

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 definition, then differentiation, then when-to-use, then exclusions, then arguments — a deliberate and useful order. Despite its density, every clause carries information the agent would otherwise have to guess.

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?

For a read-only inference tool with rich annotations, a 100%-covered two-parameter schema and an output schema, this description covers the remaining gaps: what makes this inference distinct, when it is worth the extra cost, and which sibling to use otherwise.

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 thorough chain and address semantics (0x vs base58, chain-matching requirement) are already fully documented in the schema. The description only restates the two argument names and adds a cost note, which is a baseline-3 contribution rather than added parameter meaning.

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 resource and mechanism: clusters of wallets acting as one actor, inferred behaviourally even without transfer or funding links. It explicitly contrasts that inference with get_wallet_links' proven links, so an agent can separate the two without 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?

Gives a concrete triggering condition ('supply looks distributed across many small wallets and the insider graph comes back clean'), a recommended corroborating call (get_fee_fingerprint), and an explicit exclusion list naming three siblings with the condition each covers instead. Nothing is left to inference.

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