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

With no annotations, the description carries the full burden and mostly succeeds: it discloses the payment requirement and price ($0.01 USDC on Base via x402), the billing model ('one price for the whole list'), the change-detection thresholds (owner/authority changes, liquidity or price moves of 10%+), and a liability caveat ('rules-based, not advice'). It does not cover partial-failure behavior (what happens if one of five tokens is unsupported or unresolvable) or rate limits on polling.

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 action and scope, and every clause adds information (chains, return fields, diff semantics, pricing, disclaimer). The single dense run-on sentence with multiple colons is harder to scan than a short structured breakdown would be.

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?

There is no output schema, so the description must carry the return contract — and it does, enumerating risk score, level, reason codes, price, liquidity, fingerprint and an alerts list. Combined with the pricing model, polling intent and diff thresholds, an agent has everything needed to invoke this correctly on a schedule.

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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: it explains the fingerprint→since round-trip purpose and what returning those fingerprints buys you ('what changed'), which the schema only states mechanically. It still defers the token string syntax and defaulting rules entirely to the schema.

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 with hard scope: 're-check up to 5 tokens you hold or watch in one call' across six named chains, with the exact fields returned. An agent can tell this is a batch, incremental re-check tool rather than a one-off lookup. It never names the obvious near-duplicate sibling (token_risk_check) or the per-chain *_token_snapshot tools, so differentiation is inferred from

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 operating context: 'made for polling positions on a schedule' and 'send the fingerprints back as since to get what changed,' which tells the agent this is the repeat-call variant, not the first-look tool. It stops short of explicit exclusions (e.g., 'for a single ad-hoc token check use token_risk_check instead') or first-call guidance.

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