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

Annotations already cover readOnly/idempotent/openWorld, but the description adds material context the schema does not: a per-call price ($0.02 USDC via x402 on Solana), a paywalled-call implication, an alternate HTTPS GET endpoint, the external data sources (OFAC-SDN, mixer lists, live allowance data), and an explicit 'heuristic only, not a compliance determination' caveat. These are exactly the operational facts an agent needs before invoking a paid, open-world 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 tight sentences: the first front-loads the capability and its three signal families, the second carries the safety/pricing contract. Nothing is repeated from the schema or annotations verbatim, and the endpoint URL is compactly appended rather than given its own paragraph.

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 no output schema, the description compensates by naming what is checked (age/activity, list matches, allowance exposure) so the agent can anticipate result content, and it covers cost, safety profile, and chain coverage. It stops short of describing the response shape (score vs. flag list) or latency/rate-limit behavior, which would be the remaining 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?

Schema description coverage is 100%, so every parameter (address auto-detected family, chain enum, lookback_blocks, deep) is already documented in the schema. The description adds only the parenthetical '(EVM)' qualifier on the approval check and the Solana/EVM split, not new semantics for any individual parameter. Baseline 3 applies.

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+resource ('heuristic risk screen for a Solana or EVM wallet') and enumerates the three signal families it returns: activity/age, sanctions/mixer matches on the address and counterparties, and EVM token-approval exposure. The wallet-level composite scope is distinguishable from point tools like sanctions_screen or evm_allowance, though the description never names an alternative to route away to.

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?

The word 'Basic' plus the existence of a `deep` flag implies a lighter/cheaper tier, and the disclaimer 'not a compliance determination or security guarantee' tells the agent how much weight to place on results. But there is no explicit when-to-use/when-not guidance and no pointer to sanctions_screen, sol_token_risk, or evm_allowance for deeper or narrower checks.

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