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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: every response reports which lists were checked and how current they were, each match links to its official source, and pricing is $0.01 per name screened. It does not cover failure modes (e.g. all parameters optional — what happens with no names) or result-size limits, so it is useful but not rich.

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 scope, then use cases, then the wallet-check and price caveat; every sentence carries information. The long enumeration of list names partially duplicates the lists enum in the schema, which is the main redundancy, but it usefully communicates screening breadth.

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 six optional parameters and no output schema, the description does the right work by explaining the shape of the answer (lists checked, currency, sourced matches) and the per-name pricing model. Gaps remain: it does not state that all parameters are optional / what an empty call does, nor how the 50-item caps, minScore threshold, or country filter affect results.

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%, so the enum values, maxItems and minScore range are already documented, which sets the baseline at 3. The description contributes one real semantic addition — that crypto addresses are matched exactly against OFAC-listed addresses rather than fuzzily, distinguishing the addresses parameter's behavior from the name matching — plus the "one or many names" batching hint, but says nothing about how country or entityType narrow results.

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 concrete question it answers ("is this company, vessel or person sanctioned?") and enumerates the exact source lists (OFAC SDN/non-SDN, US CSL, UK, EU, UN), plus the crypto-address variant. That scope is clearly distinct from siblings like company_check or identifier_resolver, so an agent can pick it without opening the schema.

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?

Names concrete usage contexts — KYB, compliance, procurement checks, and screening a wallet before an agent pays — which tells the agent when this tool is appropriate. It stops short of explicit routing (no "use company_check instead when…"), so there is no negative guidance or named alternative.

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