PEP (Politically Exposed Person) check via Wikidata. AMLR Art. 22 enhanced CDD for PEPs.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Full name e.g. 'Vladimir Putin', 'Angela Merkel' | |
| country | No | Country to narrow search (optional) |
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 only reveals the data source (Wikidata) and regulatory context, without disclosing limitations, return format, or side effects. The absence of an output schema further amplifies the gap.
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 short sentences that immediately state the tool's purpose and regulatory relevance. It is front-loaded and contains no unnecessary words.
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?
Without an output schema, the description should explain what the check returns (e.g., whether the person is a PEP). It also lacks any mention of data freshness, limitations, or behavior when no match is found, making it insufficient for an AI agent to fully understand the tool's output.
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 input schema already provides complete descriptions for both parameters, including an example for 'name' and the optionality of 'country'. The description adds no additional meaning beyond the schema, so it does not compensate for any missing information.
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 'PEP (Politically Exposed Person) check via Wikidata', identifying the tool's function with a specific verb and resource. It distinguishes from sibling tools like sanctions_screen and adverse_media by focusing on PEP screening.
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 mention of 'AMLR Art. 22 enhanced CDD for PEPs' implies a compliance context, but the description does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. Guidance is implied rather than explicit.
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.
Each tool targets a distinct AML function: sanctions screening, PEP checks, adverse media, country risk, transaction risk, UBO lookup, and regulatory news. The only potential overlap is between health_check and watchlist_update, but their purposes (server status vs data refresh) are clearly separated.
All names are lowercase with underscores and descriptive, but the pattern mixes noun phrases (adverse_media, transaction_risk) with verb phrases (pep_check, sanctions_screen). This is mostly consistent but not a strict verb_noun convention.
Twelve tools is well within the optimal range for a specialized AML screening service. Each tool adds a distinct capability without redundancy, making the set feel appropriately scoped.
The tool set covers the major AML workflow: sanctions screening, PEP, adverse media, country risk, transaction monitoring, UBO identification, and regulatory intelligence. It also includes operational tools (health check, watchlist update), leaving no critical gaps for the stated domain.