Generate a 0-100 jurisdiction risk score using FATF black/grey list status, Basel AML Index, and sector risk indicators.
| Name | Required | Description | Default |
|---|---|---|---|
| sector | No | Business sector (optional) | |
| entity_name | Yes | Entity name | |
| jurisdiction | Yes | ISO 2-letter country code |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full burden. It does provide useful behavioral context by explaining the methodology and the numeric output range. However, it does not disclose whether the score is cached or live, whether it may call external services, what happens with an invalid or unsupported jurisdiction, or any rate-limiting concerns.
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 a single, well-structured sentence with no wasted words. It front-loads the most important information: what the tool generates, the output range expected, and the inputs used to calculate the score.
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?
The description captures the output and method, but without an output schema or annotations, it leaves some operational gaps, such as what the returned payload looks like, whether plausible entity data is required, and how edge cases are handled. Still, the essentials for invoking the tool and interpreting the primary output are present.
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 coverage is 100% and the schema already provides descriptions for all parameters, so the baseline is 3. The description adds some useful semantics by linking 'sector' to sector risk indicators, but it does not clarify important edge cases such as jurisdiction format, entity contribution, or how to pass unsupported jurisdiction codes.
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 identifies the tool as generating a jurisdiction risk score, states the numeric output range (0-100), and names the key data inputs (FATF list status, Basel AML Index, sector indicators). It is specific enough to stand apart from the sibling tools by intent, though it does not explicitly contrast itself with screen_sanctions or verify_entity.
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 usage context is implied by the description: this is the tool to call when a jurisdiction risk score is needed, unlike sanctions screening, ownership mapping, or entity verification. However, it does not explicitly state when to prefer this tool over sibling tools, nor does it describe exclusions or alternative tools.
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 intelligence function: ownership mapping, jurisdiction risk scoring, sanctions screening, and entity verification. While some data sources overlap, the purpose and output of each tool are clearly separable.
All tool names follow a consistent verb_noun pattern: map_ownership, score_risk, screen_sanctions, verify_entity. The verb clearly indicates the action and the noun clearly indicates the subject, making the naming predictable and intuitive.
Four tools is a well-scoped set for an entity intelligence API. Each tool covers a meaningful and distinct part of the domain without redundancy or bloat.
The core entity intelligence workflow is covered: verify the entity, check ownership, assess risk, and screen for sanctions. Minor gaps exist, such as no explicit search/discovery tool or historical monitoring, but the primary lifecycle is complete.