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

Annotations already cover read-only/idempotent safety, and the description adds substantial non-obvious behavior: a 3-hop traversal limit, the source of exchange labels (public label set), a snapshot-based coverage restriction, tiered access returning only a summary preview without a key, and an explicit "patterns only, not findings about any person" framing. These are exactly the operational and interpretive constraints an agent needs before calling.

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?

Front-loaded with the core output promise before scope, disclaimers, and paywall notes. Dense but every clause carries information; the parenthetical enumerations of exchanges and wallet-group contents are slightly heavy for a single paragraph but do not waste space.

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, so the description carries the return-value burden and does so by listing the returned artifacts (cash-out trail, deposit addresses, funding source, wallet group stats). Coverage limits and license gating are disclosed; only the concrete response shape/field layout is left unspecified, which is a minor gap.

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 a single parameter and 100% schema coverage, the schema already defines the base58 Solana address. The description adds a bit of semantic context (the wallet is typically a token creator and must be in the forensics snapshot), which constrains what values make sense beyond format alone.

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 ("for a Solana wallet ... return where its SOL/USDC went") and enumerates exactly what comes back: transfers up to 3 hops, exchange hot wallets, deposit addresses, funding source, wallet group. None of the sibling tools (token_manipulation_score, kol_scorecard, check_token) do wallet fund-flow tracing, so it is clearly differentiated.

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?

Gives clear applicability context: the wallet is "typically a token creator" and must be "in the current forensics snapshot (creators of flagged impersonation coins, serial launchers, creators of KOL-called tokens)", which implicitly excludes out-of-snapshot wallets. It also flags the paywall condition ("Without a trial/paid key: summary preview"). It stops short of naming an explicit alternative tool for non-snapshot wallets.

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