ARM Verify — Entity Intelligence API

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

With no annotations, the description carries the full behavioral disclosure burden, and it does so thoroughly: it details the exact JSON return fields, names the data sources (GLEIF, Companies House PSC, OpenCorporates), and candidly warns that the depth parameter is accepted but not yet enforced. It also adds operational context around logging and billing, so an agent can predict the tool's behavior accurately.

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 long but every sentence carries distinct information: purpose, return shape, sources, use cases, and operational constraints. It is front-loaded with the core purpose and then flows logically into output and caveats, making it easy for an agent to scan.

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?

There is no output schema and no annotations, but the description compensates by enumerating the return object fields, data sources, use cases, and critical behavioral caveats. An agent has enough context to invoke the tool and interpret its results correctly.

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 covers all four parameters with 100% coverage, so the baseline is 3, but the description adds meaning beyond the schema: it notes that depth is ignored in the current implementation, that UK (GB) entities return the richest data via PSC, and that registration_number makes UK lookups exact. This materially improves correct invocation.

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 opens with a specific verb ('Trace') and a concrete resource ('the corporate ownership chain above a company'), and clarifies the end goal (identifying natural persons who ultimately control it). This distinguishes it from sibling tools like score_risk and screen_sanctions, which target risk scoring and sanctions matching rather than ownership mapping.

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?

It explicitly states when to use the tool: 'USE WHEN beneficial-ownership disclosure is required under AML or KYC rules, or to detect ownership by a sanctioned parent.' It does not name sibling alternatives or state when not to use them, so it stops short of full routing guidance; nevertheless the use cases are clear.

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

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 that usage is logged but not billed, that the tool is called via MCP, that it screens entity_name against sanctions lists, and that jurisdiction is the single largest input. It also explains the meaning of the score scale. It doesn't mention rate limits or whether the score is cached, but for a read-only scoring tool this is strong disclosure.

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 dense but well-organized: it front-loads the core purpose and return format, then sources, then usage guidance, then billing note. Every sentence adds information. It is longer than average, but the length is justified by the rich return payload and the need to distinguish from siblings.

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 tool with no output schema, the description thoroughly documents the return JSON fields, their types, and example values. It also covers data sources and usage context. Minor gaps: no mention of error conditions (e.g., invalid jurisdiction code) or whether the tool is synchronous, but the description is largely complete for an agent to call it correctly.

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%, so the baseline is 3. The description adds value by explaining that entity_name is also screened against sanctions lists, that jurisdiction is the single largest input via FATF and Basel AML Index, and that sector is optional with examples. This goes beyond the schema's field descriptions.

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 states a specific verb ('Produce'), a precise resource (composite 0-100 financial-crime risk score), and the inputs (jurisdiction, sector, sanctions exposure). It also names the return fields, which distinguishes it from siblings like screen_sanctions (which likely returns raw hits) and verify_entity (which likely returns identity data).

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?

Explicitly says 'USE WHEN you need a single comparable risk figure for onboarding thresholds, portfolio ranking or periodic review.' It also contrasts with the REST API for metered billing, and the sibling names (screen_sanctions, verify_entity) imply alternatives for raw screening or verification. This is clear when-to-use guidance.

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

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses the return shape, the specific sanctions lists, approximate dataset sizes, daily refresh time, matching behavior like token-based/case-insensitive matching, and billing distinction between MCP logging and metered REST API usage.

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 long but every section earns its place: action, return contract, data sources, freshness, use case, and billing. It is front-loaded with the core purpose and output, and the additional details are structured in clearly separated sentences rather than as an unstructured wall of text.

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 is complete for a tool with no output schema: it enumerates all return fields, their possible values and types, source lists, update schedule, expected dataset scale, and invocation context. An agent has enough information to decide when to call it and to interpret its result without guessing.

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 100% parameter coverage with detailed descriptions, examples, and constraints, so the baseline is 3. The description adds overall screening context but does not extend parameter-level semantics beyond what the schema already states.

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 opens with a specific verb and resource: 'Screen a company or person against consolidated government sanctions lists and a politically-exposed-person dataset.' It also defines the use case ('clear a counterparty before payment, onboarding, or any transaction with sanctions exposure'), which separates it from siblings like map_ownership or score_risk by its purpose.

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?

It explicitly states when to use the tool: 'USE WHEN you must clear a counterparty before payment, onboarding, or any transaction with sanctions exposure.' It gives a clear context but does not name sibling tools or state when not to use it, so it stops short of full alternative-based guidance.

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

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 shape (JSON fields and enums), the data sources, the query order ('jurisdiction-specific registry first and falls back to GLEIF'), and that usage is logged but not billed – substantial transparency about behavior and side effects.

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 long but tightly organized into RETURNS / SOURCES / USE WHEN / billing sections; each sentence carries distinct information. The source list and field enumeration are justified because there is no output schema, though a shorter version could trim the registry roll-call.

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 tool with no annotations and no output schema, the description is remarkably complete: it defines the return contract, lists supported registries, explains fallback and billing, and the input schema covers all parameters. An agent has everything needed to decide whether and how to call it.

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%, with rich per-parameter descriptions and examples, so the description need not repeat parameter semantics. The description adds only tangential context (e.g., that jurisdiction determines the registry queried), which keeps it at the baseline for fully documented schemas.

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 action ('Verify that a company is really registered') with a clear resource (official registry record), and the returned fields make the output unambiguous. The purpose is clearly distinct from the sibling tools (map_ownership, score_risk, screen_sanctions), which target different concerns.

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?

Explicit 'USE WHEN' guidance names three concrete triggers: confirming legal existence, checking active status, or resolving an LEI before onboarding. An alternative channel (metered REST API) is mentioned, but it does not spell out when this tool should not be used versus sibling tools, so it is clear but not exhaustive.

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