AgentEconomy Compliance API

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

The description adds meaningful behavioral context beyond annotations: it mentions the Jaro-Winkler fuzzy matching algorithm, the exact cost, and the X-PAYMENT authentication requirement. It also states the return fields. It does not elaborate on the destructiveHint, leaving that annotation unexplained, but the side-effecting payment behavior makes the annotations non-contradictory.

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 four sentences, front-loaded with purpose, then returns, algorithm, cost, and authentication. Every sentence adds critical information with no fluff or repetition of the 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?

Given the absence of an output schema, the description adequately lists the key return fields, and it covers prerequisites (payment header) and cost. It does not address error handling or failover scenarios, but for a screening tool this is reasonably 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?

Schema coverage is 100%, so the parameter descriptions already document every field. The description adds modest value by indicating that fuzzy matching applies to entity names and that the tool returns sanctions match details, but it does not enrich parameter semantics meaningfully.

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 action ('Screen an entity against AML watchlists'), names concrete resources (OFAC SDN, UN sanctions), and lists expected return values (risk level, risk score, recommendation, sanctions match details). This clearly differentiates from sibling tools like kyc_check or risk_report by focusing on AML-specific watchlists and output.

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 clearly communicates when to use the tool: when AML watchlist screening is needed. It also provides necessary usage prerequisites such as the signed X-PAYMENT header and cost per screening. However, it does not explicitly contrast with sibling tools or state exclusions, so it stops short of full alternative 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?

Annotations provide readOnlyHint=false and destructiveHint=true, so the description doesn't need to restate those. It adds meaningful operational details: cost per check, signed X-PAYMENT header requirement, and data source (OFAC SDN + UN Security Council). It also discloses return fields. This goes beyond the annotations, though it doesn't elaborate on the destructive side effect implied by the annotation.

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?

Description is compact and front-loaded with the core purpose, followed by return info, data source, and cost/auth details. Every sentence provides essential information without redundancy. No fluff or filler.

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 moderate complexity and no output schema, the description covers the main behavior, outputs (verification status, risk score, matches), and operational requirements (cost, header). It lacks guidance on parameter combinations or when to use this vs sibling tools, which is a notable gap but not critical given the schema and annotations.

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 all four parameters described. The description doesn't add extra meaning about parameter formats or how they interrelate (e.g., wallet_address vs entity_id). Since the schema already handles parameter semantics, the baseline score of 3 applies—no additional value from the description.

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?

Description states a specific verb ('Run') and resource ('KYC identity verification check') with clear targets (OFAC and UN sanctions lists). It also mentions returns like risk score and sanctions/PEP matches, which differentiates from generic screens. However, it doesn't explicitly contrast with sibling tools like aml_screen or wallet_screen, so it falls short of 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?

No guidance on when to use this tool vs alternatives such as aml_screen or wallet_screen. It mentions prerequisites (payment header) but not when this tool is preferred or when it should be avoided. The description implies a KYC use case but lacks explicit context or 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?

The description adds significant context beyond annotations: cost ($0.10 USDC), payment header requirement, and a summary of return fields. While annotations already flag destructive/readOnly/idempotent hints, the description supplements with operational and cost details.

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?

Two sentences, front-loaded with the main verb and resource. Every sentence is purposeful: first states purpose, second covers return values, cost, and payment. No redundancy or filler.

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 complex tool with no output schema, the description covers purpose, return values, cost, and payment. It could benefit from explicit guidance on when to use vs siblings, but annotations and schema fill some gaps. Overall this is a complete and useful description.

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 parameters are already documented. The description references the combination of KYC/AML/jurisdiction analysis which maps to entity_type, wallet_address, and include_transaction_analysis, but does not add new syntax or format details beyond the schema.

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 explicitly states the tool's function: generate a comprehensive regulatory risk assessment report combining KYC, AML, and multi-jurisdiction analysis. This clearly distinguishes it from the sibling tools (aml_screen, kyc_check, wallet_screen) which focus on individual components.

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 implies use for a comprehensive risk assessment needing KYC+AML+multi-jurisdiction, but does not explicitly state when to choose this over individual sibling tools or provide exclusion criteria. No alternatives are named, so guidance is only implied.

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?

Beyond annotations, it discloses a $0.05 USDC cost, the required X-PAYMENT header, return values (risk level, score, recommendation), and the specific analysis scope. It does not fully elaborate on the destructiveHint annotation's meaning, but the payment side-effect is a critical behavioral 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?

Four concise sentences front-load the core purpose, then pack in essential operational details (cost, payment header, outputs). There is no redundant phrasing, and every sentence earns its place.

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 explains inputs, outputs, cost, authentication requirement, and analysis dimensions, which is substantial for a tool without an output schema. It lacks interpretation guidance for risk scores, but overall it gives the agent enough context to invoke and use the tool 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 single parameter wallet_address is fully described in the schema with format details (0x + 40 hex chars). The description adds no new parameter-specific information, so the schema carries the burden; 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?

The description opens with a specific verb+resource pair: 'Screen a blockchain wallet address for compliance risk.' It then details the unique combination of OFAC check and on-chain exposure analysis across Ethereum and Base, clearly distinguishing it from siblings like kyc_check or aml_screen.

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 implies usage context by explaining what the tool does and noting 'No entity name required,' but it does not explicitly state when to use this over alternative tools or mention any exclusions. Sibling differentiation is implicit rather than direct.

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