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

With no annotations, the description carries the full burden and does well: it discloses that calls cost $0.01 USDC on Base via x402, that scoring is rules-based rather than advice, and that results are diffable via a returned fingerprint. It stops short of latency, rate limits, failure modes, or caching behavior.

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 question and answer shape; nothing is padding. The long enumerated list of risk factors is dense but earns its place by defining the check's scope, though the single run-on sentence is harder to scan than it needs to 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?

With no output schema and no annotations, the description still tells the agent what comes back (score, plain-language reasons, underlying facts, price, liquidity) and the cost/payment mechanism. Only error behavior and response field layout are left unspecified, which is acceptable for a read-only scoring 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 coverage is 100% and the schema already documents chain defaults and the 'since' fingerprint semantics, so the description mostly restates them. It does add one genuinely new detail — that the fingerprint is returned as 'watch.fingerprint' — which matters because there is no output schema, but that is a marginal gain.

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?

Opens with the question it answers ('Is this token safe?') and names a specific deliverable: a 0-100 rug-risk score with enumerated reasons, backing facts, and USD price/liquidity. The risk-scoring framing cleanly separates it from the per-chain *_token_snapshot siblings, which return raw token data rather than an aggregated verdict.

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?

States the applicability surface precisely (any token on six named chains) and explains the incremental-call pattern: send back the fingerprint as 'since' to get a diff. It also flags the x402 payment path, which is decision-relevant. No explicit when-not or named alternative (e.g., use *_token_snapshot for raw metadata) is given.

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