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 burden and does so well: it discloses the billing model ($12.00 per call, refused when balance is too low, bank portal sessions free), the three data sources consulted, and the output's confidence/complexity signals. It omits rate limits and error/coverage-failure behavior, leaving a minor 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?

Front-loaded with the core purpose, then organized under clear RETURNS/SOURCES/USE WHEN/BILLING markers. It is dense and somewhat long, but each block (output shape, sources, billing) earns its place given the absent output schema.

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?

No output schema exists, so the description must — and does — enumerate the return structure in detail (ownership_chain, natural_persons, natures_of_control, lei, complexity, data_confidence, notes). For a high-complexity ownership-tracing tool it is nearly complete, missing only explicit coverage limitations and auth/prerequisite notes.

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 all four parameters are already documented with examples, ranges and notes. The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate.

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 verb and resource ('Trace the corporate ownership chain above a company') plus the end goal ('identify the natural persons who ultimately control it'). This is clearly distinct from the screening/verification siblings, so an agent can route to it without ambiguity.

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?

Gives explicit triggering conditions: 'USE WHEN beneficial-ownership disclosure is required under AML or KYC rules, or to detect ownership by a sanctioned parent.' No named alternatives or when-not guidance against verify_entity/screen_sanctions, so it stops short of a 5.

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, the description carries the full burden and delivers: it discloses the exact output fields and their value ranges, the underlying data sources (FATF, Basel AML Index 2025, live sanctions screening, ARM classification), and an implicit side effect — entity_name is screened against sanctions lists. It also states the billing model ($12.00 per call, charged to API-key credits, refused on low balance, free for bank portal sessions), covering cost and a failure mode.

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 purpose, then returns, sources, use-when and billing in a single scannable block using ALL-CAPS labels. Given there is no output schema, the enumerated return fields are load-bearing rather than padding, and no sentence is wasted.

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?

Despite having no output schema and no annotations, the description fully compensates: return values and their ranges are spelled out, sources are named, the billing/failure behavior is disclosed, and usage scenarios are given. Nothing an agent needs to invoke this three-parameter tool correctly is missing.

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 schema already documents all three parameters including examples, enum-like value hints and the note that jurisdiction is the largest scoring input. The prose only restates that the score derives from jurisdiction, sector and sanctions exposure; it adds little beyond the schema, so the baseline 3 applies.

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 names a specific verb and artifact — produce a composite 0-100 financial-crime risk score for a company — and enumerates the three driving inputs (jurisdiction, sector, sanctions exposure). This clearly separates it by output type from siblings like screen_sanctions and verify_entity, but no sibling is named or explicitly excluded, which is the rubric's threshold for a 5.

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?

"USE WHEN you need a single comparable risk figure for onboarding thresholds, portfolio ranking or periodic review" gives concrete triggering scenarios. However, it never states when NOT to use it or points to screen_sanctions/verify_entity as the alternative for single-purpose lookups, so the guidance is clear but lacks explicit exclusions.

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, the description carries the full burden and does well: it discloses the exact cost ($4.00 per call, refused on low balance, bank portal sessions exempt), data provenance and daily 03:00 UTC refresh, the four source lists and their sizes, and the full return shape including evidence. It never explicitly states the call has no side effects / is a read-only computation, which is the one behavioural trait left implicit.

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?

It is long, but it is front-loaded (purpose, then return shape, then sources, then when-to-use, then billing) and the return enumeration earns its space because there is no output schema. Some of the source-list sizing and evidence-field detail is more than strictly needed for tool selection.

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 screening tool with no output schema and no annotations, the description covers what the agent needs: what is screened, against which lists, how fresh the data is, what the response contains, what it costs, and when to call it. Nothing material is missing.

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 entity_name, entity_type, country and threshold are already fully documented in the schema, including defaults, ranges and the >=0.90 MATCH rule. The description adds no parameter-level syntax or format detail beyond that, so the baseline 3 applies.

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 verb (screen) and resource (company or person against government sanctions lists plus a PEP dataset), and the sibling set (map_ownership, score_risk, verify_entity) is clearly not what this does — none of them screen against sanctions lists. The purpose is unambiguous from the first sentence.

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?

"USE WHEN you must clear a counterparty before payment, onboarding, or any transaction with sanctions exposure" gives a concrete triggering context. It stops short of naming an alternative sibling (e.g. verify_entity) or stating when NOT to use it, so it is clear context without exclusions.

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, the description carries the full burden and does so well: it discloses billing ($1.50 per call charged from API-key credits, refused when balance is too low, bank portal sessions free), the data provenance (17 named registries), and the resolution strategy (jurisdiction-specific registry first, GLEIF fallback). This is exactly the cost/auth/source behavior an agent needs before invoking a paid external lookup.

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 purpose, then returns, sources, fallback, usage, and billing in a logical order. The 17-registry enumeration is bulky but arguably load-bearing for a jurisdiction-scoped tool, so it is defensible rather than wasteful.

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 the description compensates fully by enumerating every returned field (including the status enum values and null-able LEI) plus source registries, fallback order, and billing semantics. An agent has everything needed to call it and interpret the response.

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 beyond the schema by explaining that the jurisdiction parameter selects which national registry is queried and that GLEIF is the fallback, and the SOURCES list lets the agent anticipate coverage gaps for a given country code.

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 a specific verb and resource: 'Verify that a company is really registered, and return its official registry record.' That is clearly distinct from siblings like screen_sanctions, score_risk, and map_ownership, which involve different operations on the same 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?

'USE WHEN you need to confirm a counterparty legally exists, is still active, or to resolve its LEI before onboarding' gives concrete trigger conditions. It lacks an explicit when-not statement or a named alternative among the sibling tools, so it stops short of a 5.

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