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

Beyond the annotations (readOnlyHint, idempotentHint, non-destructive), the description adds genuinely valuable behavior: the fail-closed semantics — 'a check that did not run never reads as clean, so GO means everything material was actually screened' — is exactly the kind of nuance an agent needs to trust a GO verdict. It also discloses pricing, the x402/x-credit-token payment model, the free-call tier, and that no wallet/API key is required. No contradiction with annotations.

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?

The description is dense but every sentence carries operational weight: verdict format, screening factors, fail-closed semantics, pricing, and requirements. It is front-loaded with the purpose and verdict concept. Minor non-essential content like 'Not financial advice' and the detailed credit-header payment explanation could be trimmed, but they don't significantly bloat.

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?

For a single-param tool with an output schema and rich annotations, the description covers purpose, verdict semantics, screening scope, failure behavior, and commercial constraints. It does not route the agent among the many risk-adjacent siblings (safe_check, compliance_check, address_trust, sanctions), which is the main completeness gap, but nothing essential to invoking the tool correctly is missing.

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% for the single address parameter, and the schema already describes it as 'Address you are about to send to'. The description restates it as 'Required input: address' and frames it as the destination of a pending send/approve/sign, but adds little semantic value beyond the schema. Baseline 3 is appropriate.

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?

The description clearly states what the tool does: it returns a single GO/REVIEW/STOP verdict on whether an address is safe to send, approve, or sign to. It enumerates the specific factors screened (OFAC sanctions, identity, wallet-vs-contract, address age, post-send contract logic swap), which gives an agent a precise mental model and clearly differentiates it from sibling tools like address_intel or sanctions.

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 opening line — 'Before your agent sends, approves or signs to an address' — is an explicit trigger condition naming exactly when to invoke this tool. It does not, however, name any sibling alternatives or state when not to use it (e.g., a sanctions-only check could use the sanctions tool), so it misses the explicit exclusion/alternative guidance of the highest tier.

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