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

Beyond the readOnlyHint/openWorldHint annotations, it discloses the cost model ($0.003 USDC per successful call), the payment rails (x402 on Base, Solana or Arc), and that failed calls are not charged — critical context for a paid tool. It also proactively discloses the analytical limitation (no scam/exploit template database), preventing over-reliance on the result.

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 what is computed and the output scale, then scope limit, then price. Four sentences, all earning their place, though the metric parentheticals make it denser than typical; minor tightening possible without losing the pricing detail.

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?

An output schema exists and return values are not over-explained, yet the description still names the score range and label set. For a read-only, two-parameter, paid tool it covers computation, scope limits, and billing — everything an agent needs to call it correctly.

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 both parameters are self-documented as 40-hex addresses, so baseline is 3. The description adds real semantics the schema lacks: the inputs must be Ethereum contracts' runtime bytecode targets, i.e. deployed contract addresses rather than arbitrary hex or EOAs, which is a meaningful constraint.

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 (compares) plus the exact resource (runtime bytecode of two named Ethereum contracts) and enumerates both metrics used (Jaccard on PUSH4 selectors, cosine on opcode frequencies) and the output shape (0-1 score with SIMILAR/PARTIAL/DIFFERENT). This is clearly distinguishable from nearby siblings such as smart_contract_linter_audit or token_composite_safety_score, which do not do pairwise bytecode comparison.

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?

It states a firm usage boundary — 'compares two addresses only' and 'cannot say a contract is a known clone' — which tells the agent when to route elsewhere (e.g. known_scams_blacklist_db) for template matching. It does not name that alternative explicitly, so the exclusion is clear but the redirect is left to inference.

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