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

Goes far beyond the readOnlyHint/openWorldHint annotations: exact price ($0.002 USDC / 2000 base units), the x402 payment flow, that unpaid HTTP calls return 402 even for invalid queries, that signed calls with invalid arguments are rejected before settlement and not charged, and that charging only occurs on non-error results. It also discloses cache behavior — cached, stale, and cacheAgeMs — and explains that stale=true means a prior result was served during refresh or upstream failure.

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?

Purpose is front-loaded correctly, but the payment portion repeats itself: the price is stated, then restated for HTTP GET, then the no-charge-on-error rule is stated twice in different words. The trailing bracketed vendor/payment boilerplate duplicates information already given earlier in the prose, diluting a description that would be stronger at two-thirds the length.

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?

No output schema exists, and the description compensates by enumerating the returned fields, the scoring components, and the cached/stale/cacheAgeMs envelope semantics. Combined with the full payment and caching disclosure, an agent has everything needed to call this correctly and interpret the result.

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 single address parameter is fully documented in the schema (base58, 32-44 chars, with a worked example), so the schema carries the weight. The description adds nothing about the address itself, which is acceptable but yields only the baseline score at 100% coverage.

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 verb and resource ('cheap copy-trade screen for one wallet') and enumerates exactly what comes back: windowed realized PnL, win rate, closed trades, bot/exchange flags, copyTradeScore and copyTradeGrade with its component math. It also distinguishes itself from the paid full report (/wallet/profile) and the free teaser (/wallet/preview), so an agent can separate it from wallet_profile and wallet_preview without opening a 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?

'Use this for a cheap copy-trade screen before paying for a full profile' gives an explicit selection rule, and the two endpoint pointers make the alternative tiers concrete (free preview vs. full paid profile). When-not guidance is implied strongly enough by the cost ladder that an agent knows to reach for this instead of wallet_profile when price matters.

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