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

Annotations already declare readOnly/idempotent/non-destructive; the description adds what they cannot: the enumeration of checks performed, the outcome taxonomy (no_hits, review, block_review), list-version stamping, and a signed receipt artifact. It also discloses the unusual behavioral traits an agent must plan around: the 0.02 USDC x402 charge, the 10-credit API-key path, and the 5-free-calls-per-day allowance.

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 triggering use case, then checks, then return values, then input list, then cost — a sensible priority order with no filler. The second sentence is a long run-on covering three separate screens, which costs some readability against an otherwise dense, waste-free phrasing.

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 carries the return burden and does so by naming the three outcome values plus the accompanying list versions and signed receipt. Pricing, payment rails and the free-tier allowance are also covered. The remaining gap is field-level semantics for the three undocumented optional parameters.

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 only 20% (only owner is annotated), so the description does useful work by enumerating wallet, owner, owner_type, birth_year and country and marking all but the first two optional. However it never explains formats or constraints for the undocumented fields — wallet address syntax, birth_year format, or whether country is ISO-2/ISO-3 — so it only partly compensates for the coverage gap.

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 chain and resource: screens a self-hosted wallet against OFAC-listed addresses, screens the claimed owner against EU/UN/UK/US sanctions and PEP, and checks the company register, then issues an evidence record. It situates itself in a concrete compliance workflow (EU AMLR, Travel Rule) and names its outputs (no_hits/review/block_review, signed receipt), which separates it from generic siblings like eu_sanctions_wallet or pep_screen.

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?

"Use when a crypto service sends to or receives from a self-hosted wallet and must document its checks" gives a clear triggering condition tied to a workflow and jurisdiction. It lacks explicit exclusion guidance or direct naming of the alternative sibling (e.g. eu_sanctions_wallet for a plain screen without the evidence record), so routing is clear but not fully disambiguated.

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