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

Annotations already declare read-only, idempotent, open-world, non-destructive; the description adds context those cannot carry — the two evaluator modes with their trade-offs (outbound: full evaluator set, 8s budget; reverse-call: critical evaluators only, limited set), the four verdict outcomes including insufficient_evidence, the enumerated evidence categories, and a sidecar audit_url for verification. This tells the agent latency and coverage expectations 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 what the tool returns, then modes, then the usage trigger — a sensible ordering. The return-value enumeration is a long parenthetical list that verges on overstuffed, but every element (verdict vocabulary, evidence categories) carries information the agent needs since there is no output schema.

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 correctly takes on the burden of describing the return payload: verdict enum, reason_codes format, critical_flags, suggested_action, evidence map, and audit_url. Combined with mode selection, latency budget, and supported targets, an agent has everything needed to call it correctly in one shot.

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 each parameter already carries a substantive description, so the baseline of 3 applies. The prose reinforces mode semantics and target_type inference but introduces no syntax, format, or constraint details absent from the schema — much of the mode and action guidance is restated rather than added.

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 ('Returns a decision-ready answer') and a precisely scoped resource (on-chain counterparty), enumerating the target kinds: wallet, smart contract, token, DeFi protocol, bridge. An agent immediately knows what it gets back (verdict, reason_codes, flags, evidence, audit_url). It does not differentiate itself from the closely related sibling strale_trust_profile, which is the only remaining ambiguity.

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 a concrete trigger: 'Use before any agent transacts on-chain — sending value, swapping, staking, minting, bridging, or interacting with a contract,' and names the condition that selects reverse-call ('when you are an x402 service publisher gating an inbound buyer'). No exclusions or named alternatives among siblings (e.g. strale_trust_profile), so it falls short of a 5.

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