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

With no annotations at all, the description carries the full burden and does substantial work: it discloses that the call is paid, enumerates what comes back (score, verdict, evidence that moved the score, next action), and names the evidence dimensions. It does not state whether the lookup is read-only/idempotent, latency, or whether results are cached, and the text is cut off mid-sentence.

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?

Well front-loaded: the decision framing and expected output come before the use-case list, and every sentence adds information. It is slightly padded by promotional phrasing ('THE DECISION', 'in one paid call') and trails off unfinished ('so the caller can re-d'), which costs it a point.

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 no-argument tool with no output schema and no annotations, the description covers the essentials: what is returned, in what shape, and for what decisions. The remaining gaps are how the target address is bound to the call and what the 'paid' aspect costs, which an agent would want before invoking it.

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?

The schema has zero parameters, so the baseline is 4 and there is nothing schema-wise to explain. The one real ambiguity the description leaves is which wallet is evaluated — the address is evidently supplied implicitly (payment/task context) since additionalProperties is false, and the definition never explains that mechanism.

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?

Specific verb+resource: it produces a risk verdict (0-100 score plus PAY/CAUTION/AVOID) for a wallet address, framed around a concrete decision ('should you settle an invoice to this address?'). It clearly distinguishes a decision tool from a plain data lookup, but never names or contrasts the very similar siblings akari_wallet_verdict and akari_wallet_intel, so the agent must guess which of the three to call.

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?

Explicit usage contexts are given: x402 seller vetting, prepay-or-not calls, invoice risk caps, airdrop allowlist screening, i.e. when to reach for this tool. What is missing is the inverse — no when-not guidance and no named alternative for callers who only want raw wallet facts rather than a verdict.

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