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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real context beyond them: the output is deliberately truncated to verdict + grade only, and there is a 10/hour quota shared with a sibling tool. It stops short of saying anything about latency, caching, or how stale a verdict may be.

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 free tier label, then output scope, then quota, then the paid alternative. Zero filler and nothing buried.

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?

With an output schema present, the description does not need to explain return values, and it still covers cost, quota, truncation and the upgrade path. The one completeness gap is the chain list mismatch against a 13-value enum, which is the most likely source of a mis-call.

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% and the address field already documents every supported address format (base58 mint, 0x contract, CURRENCY.rIssuer, Algorand asset id). The description adds no format or validation detail of its own, and its 'Solana or EVM' phrasing arguably under-specifies rather than enriches the enum.

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?

It states a concrete verb and resource — return the green/orange/red verdict and grade for a token — and explicitly contrasts itself with the paid sibling token_verdict. The only blemish is scope: it says 'for a Solana or EVM token' while the schema's chain enum also covers xrpl, algorand, monad, robinhood and others, so an agent could wrongly conclude those chains are unsupported.

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 names the decision moment ('a token your agent is about to buy, hold or accept') and routes to token_verdict ($0.01) when the reasons, one-line summary or market data are needed. The free-quota condition (10 calls/hour, shared with presign_quick_check) is stated so the agent can decide whether to spend a call.

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