Screen a person or company name against official sanctions lists: OFAC SDN, OFAC Consolidated (US Treasury) and UK OFSI. Returns hit/risk (clear|review|high) with the matching entries. Use for AML/KYC/KYB compliance before onboarding or paying a counterparty.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Person or company name to screen |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the return type (hit/risk with clear|review|high and matching entries), which is useful behavioral context. However, it does not mention side effects, authentication needs, rate limits, or potential false-positive behavior. For a screening tool, more transparency about how matches are determined would be valuable, but the basic output is covered.
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 two sentences with no redundancy. It front-loads the core function and lists, then states the compliance use case. Every word serves a purpose, and it is efficiently structured.
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 simple one-parameter tool with no output schema, the description covers the essential information: what it screens, the specific lists, the return format, and the use case. It could mention potential limitations or whether the check is real-time, but given the tool's simplicity, this is largely complete.
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?
The single parameter 'name' is fully described in the schema ('Person or company name to screen'), and the description does not add additional semantics beyond that. Since schema coverage is 100%, this meets the baseline but does not exceed it.
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 the tool screens a person or company against official sanctions lists and names the specific lists (OFAC SDN, OFAC Consolidated, UK OFSI). The verb 'screen' and resource are specific, distinguishing it from generic lookup tools. It does not explicitly contrast with sibling tools like entity_resolve or kyb_verify_business, but the purpose is unambiguous.
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 description provides a clear use case: 'Use for AML/KYC/KYB compliance before onboarding or paying a counterparty.' This gives the agent contextual guidance on when to invoke the tool. It does not mention exclusions or alternatives, but the context is sufficient for a compliance-related screen.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct by resource or function, but fx_rates vs us_treasury_fx and entity_resolve vs lei_lookup could both be plausible choices for the same request. Descriptions generally make the boundaries clear, so the overlap is minor rather than systematic.
All names use lowercase_snake_case, but there is no single naming pattern: tools like btc_network, crypto_price, and weather_forecast are noun phrases, while eu_vat_validate, lei_lookup, and sanctions_screen follow an object+operation style. This mixed convention is readable but noticeably inconsistent.
14 tools is within a reasonable range for a multi-provider data server, and most tools cover a distinct data domain. However, kyb_verify_business heavily overlaps the individual VAT, LEI, sanctions, IBAN, and entity tools, and having two FX rate tools makes the set feel slightly broader than necessary.
The main KYB/entity workflow is well covered, but the set has notable gaps: sanctions screening covers only OFAC and UK OFSi, IBAN validation is structural only, and there are no UBO or adverse-media checks. For the broader data-lookup domain, the coverage is decent but not exhaustive.