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

There are no annotations, so the description is the default fallback behavior communicator. It clearly discloses authentication and payment requirements, public onchain data scope, and the specific event/attribute types included (mixer, bridge, transfer events). It is transparent about the financial barrier and that it's purely based on public behavior, but it doesn't cover things like cache freshness or rate limiting.

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?

The description has two sentences and contains useful information throughout, but it front-loads payment details before the core purpose, which reads as a run-on. The long list of output fields is useful but also likely duplicates an output schema and partially interfere with readability.

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?

Given an output schema exists and the schema provides the chain enum, the core function and the payment/scope requirements are covered. But the description remains incomplete regarding input semantics for the optional chain parameter and doesn't clearly articulate the default or expected behavior when chain is omitted. This is a moderate gap for an agent that must construct this call correctly.

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?

With 0% schema description coverage, the description needs to explain the address and chain parameters with special care. It mentions 'wallet address' and 'across chains' but never references the 'chain' parameter directly, does not indicate whether chain is an active filter or aggregation scope, and gives no guidance on address format or default chain behavior. This is a meaningful gap.

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 'Risk profile of one wallet address across chains' and enumerates the specific output fields (risk score, mixer funding, dormancy, transaction count, protocols used, etc.). This clearly conveys the tool's verb-adjacent purpose and resource. It's a bit indirect because it doesn't begin with an imperative like 'gets', but the meaning is unambiguous and distinct from siblings.

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 conveys the broad intended use case (assessing risk of a wallet) and important preconditions around API key or alternate payment. It does not, however, explicitly mention when NOT to use this tool, what sibling tools alternatives it compares to, or how it differs from tools like situation_report, chain_brief, or deep_report. The use is implied rather than explicitly contrasted.

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