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

With no annotations at all, the description carries the whole burden and does so: it discloses the exact grading methodology (30-day realized PnL plus win rate), the output shape, the 404/free and 503/free error semantics, and a full cost model ($0.02 per call drawn from existing shop credits, new top-ups paused, failed or empty calls free). That is exceptional behavioral disclosure for an unannotated 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?

Two dense sentences, zero filler, with the core output definition front-loaded and the cost/error clauses pushed to the end where they belong. Every clause carries information an agent would otherwise have to discover by calling.

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 enumerating the returned fields and their possible values, plus error and cost behavior. The one gap is that it never says whether the wallet list is paginated or whether fewer than 10 wallets can be returned, so an agent must discover result cardinality empirically.

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, and the description beats it by stating that only Base is supported even though the chain enum exposes eight chains — a constraint the schema actively misleads on. It also implies the window parameter drives the aggregation shown. It doesn't explain how 'window' interacts with the 30-day grading horizon, so not a 5.

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 names a specific resource (top-10 smart-money wallets on a token) and enumerates exactly what each entry contains: buys, sells, net, trades, a smart/profitable/mixed/losing grade, and a smart_lean verdict. That is far more than a restatement of the name. It stops short of 5 because the closely related siblings token_whales and token_holders are never named or contrasted, so the agent must infer the distinction.

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?

'Base only for now' is a real usage constraint, but there is no explicit statement of when to pick this over token_whales or token_holders, and no guidance on which window to choose. Usage is implied by the metric set rather than spelled out, which fits the 'minimum viable' band.

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