OnchainDiligence

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

Annotations already declare readOnlyHint and openWorldHint. Description adds value by detailing parallel execution, specific data sources (Chainalysis, Companies House), and the disclaimer about no verified link, which goes beyond the annotations.

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?

Three sentences: first explains the core function, second the use case, third the return value. Front-loaded with key action, each sentence earns its place with no redundancy.

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 no output schema, the description adequately describes what is returned (two independent results plus disclaimer). Could mention error handling if one check fails, but overall sufficient for an AI agent to understand and invoke 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% with clear descriptions for wallet (EVM address) and company (UK registration number). The description mentions these types but does not add significant new meaning 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?

Description clearly states it performs combined sanctions screening and UK company KYB lookup in one call, using specific verbs and data sources. Differentiates from siblings (screen_wallet, verify_uk_company, verify_us_company) by emphasizing the parallel, combined nature.

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 targets compliance agents vetting a counterparty with both a wallet and a UK company. While it doesn't state 'do not use if only one is needed', the sibling tools cover those cases, and the context implies this tool is for combined scenarios.

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 declare readOnlyHint=true, and the description reinforces that it is a read-only screening aid. It discloses that it returns scored candidate matches with specific fields (matched name, SDN type, program) and notes that weak AKAs are not screened. This adds behavioral context beyond the annotations, though it stops short of detailing match scoring mechanics or rate limits.

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 concise, using four sentences to convey purpose, return format, scope, and limitation. It is front-loaded with the core action and resource, and every sentence adds distinct information without redundancy. The use of bold for 'SCOPE' helps structure the guidance.

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 sufficiently explains that it returns 'scored candidate matches with the matched name, SDN type, and program'. It also addresses the limitation of weak AKAs and positions the tool within the broader compliance workflow. Given the parameter count (2) and simplicity, this description is 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 description coverage is 100%, so baseline is 3. The description adds value by explaining that the tool performs 'fuzzy-match' on the name parameter, implying the algorithm handles variations. For the threshold parameter, it provides a default (0.85) and notes the trade-off between recall and precision ('Lower = more candidates, more false positives'), which is not in 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 clearly states the tool performs OFAC name screening via fuzzy-matching against the SDN list. It specifies the verb 'screens', the resource 'OFAC SDN list', and includes scope details like 'primary names + strong aliases' and 'not a determination'. The sibling tools (screen_wallet, verify_*_company) are for different verification tasks, so this description effectively distinguishes the tool's 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?

The description explicitly states the tool is for AML/KYC/sanctions compliance screening and clarifies that a match is a candidate for further investigation, not a final determination. While it doesn't directly say 'when not to use', the context of siblings implies alternatives exist. The guidance on weak AKAs and secondary identifiers provides practical usage context.

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 include readOnlyHint and openWorldHint, which description aligns with (no destructive behavior). Adds context about the oracle used and return format (sanctioned/not-sanctioned with program). No contradictions.

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?

Concise at three sentences, front-loads the core action, then provides oracle context and use cases with 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?

Given one parameter and no output schema, the description provides sufficient context about the oracle, coverage, and use cases. Could slightly benefit from mentioning any additional output fields, but not needed.

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 has 100% coverage for the single parameter 'address' with a clear description. The tool description largely restates what is in the schema, adding no new semantic details.

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?

Clearly states it screens EVM wallet addresses against Chainalysis sanctions oracle covering OFAC, EU, UN designated addresses. Distinguishes from sibling tools (verify_uk_company, verify_us_company) which focus on company verification.

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 states use cases: AML compliance, counterparty due diligence, payment screening before sending funds. Does not explicitly list when not to use, but the EVM specificity implies it's not for other chains.

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 show readOnlyHint and openWorldHint; description adds that it uses official Companies House register and authoritative open data, providing behavioral context beyond annotations.

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?

Three concise sentences covering purpose, data returned, and use cases. No waste.

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?

Single required parameter with full schema description; output is described in detail (legal status, company type, etc.) despite no output schema. Complete for a lookup tool.

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 has 1 parameter with full description; schema coverage is 100%. Description does not add extra parameter meaning beyond what schema provides.

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 it performs UK company verification and KYB lookup via Companies House, listing specific data returned. The sibling tools include verify_us_company and diligence, making the UK-specific focus distinct.

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 mentions use cases: KYB onboarding, supplier due diligence, confirming business identity. Does not provide negative guidance or alternatives for non-UK companies, but context from siblings implies that.

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 already declare readOnlyHint and openWorldHint, so description adds useful context: it returns specific data fields, is authoritative US government open data, and mentions the most recent SEC filing. No contradictions or missing behavioral traits.

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 a paragraph of three sentences plus a scope note, efficiently covering purpose, inputs, outputs, and limitations. No unnecessary words, though could be slightly more compact.

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 single-parameter tool with readOnly and openWorld annotations, the description sufficiently explains the data sources, returned fields, and appropriate use cases. Output schema is missing but not critical given the explicit field listing.

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 parameter description in the schema already explains that query accepts ticker, CIK, or company name with examples. The tool description does not add additional semantic value beyond that context.

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 clearly states the tool verifies US public companies via SEC EDGAR, returning specific entity details. It distinguishes from sibling verify_uk_company by explicitly focusing on US and from the other siblings by its specific use case.

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 for KYB and counterparty due diligence on listed US entities. Clearly scopes to public companies and funds, excluding private US companies. Does not explicitly name alternative tools but implies need for state-level registration for private companies.

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