OnchainDiligence

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

Discloses parallel execution, independent results, and a disclaimer about no verified link. Adds value beyond readOnly and openWorld 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?

Single concise paragraph, no wasted words, effectively front-loaded with the main function.

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?

Adequately describes the combined function and use case, but lacks details on result structure since no output schema exists.

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. Description adds no additional detail beyond what's 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?

Description clearly states it combines sanctions screening on a crypto wallet and UK Companies House KYB lookup. It distinguishes from sibling tools like screen_wallet and verify_uk_company by offering a combined call.

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 it's built for compliance agents vetting a counterparty with both an on-chain wallet and a UK company. Implies not to use if only one check is needed, but lacks explicit exclusion.

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=true and openWorldHint=true. The description transparently discloses the output format (scored candidate matches with matched name, SDN type, program), the scope (screening aid, not determination), and the limitation that weak AKAs are excluded. No contradictions with 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?

The description is concise at three sentences, front-loading the main purpose. It is well-structured: first the action, then output, then scope/limitations. Minor improvement could be breaking into bullet points for readability, but overall efficient.

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 explains the return format (scored candidates with matched name, SDN type, program). It covers important constraints (weak AKAs excluded, need for secondary identifiers). For a screening tool with simple parameters, this is fully 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% for both parameters, so baseline is 3. The description does not add significant new meaning beyond the schema's descriptions for 'name' and 'threshold'. The schema already explains the threshold range and default. The description's context aligns but does not enhance parameter semantics.

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 verb 'fuzzy-match' and the resource 'person or company name against the OFAC SDN list'. It specifies it screens primary names and strong aliases, distinguishes from weak AKAs, and clarifies it is a screening aid, not a determination. The purpose is distinct from sibling tools like 'screen_wallet' or 'verify_uk_company'.

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 when to use: for AML/KYC/sanctions compliance. It provides clear exclusions: weak AKAs are not screened, and a match is not a final determination, requiring secondary identifiers. However, it does not explicitly compare to sibling tools or state when not to use this tool over others.

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 openWorldHint=true, which already inform safety and data freshness. The description adds valuable context beyond annotations: the oracle reflects current designations including removals (an address may screen clean after delisting), and it explicitly states the oracle does not return programme-level case detail. This transparency about dynamic data and output limitation goes beyond what annotations cover.

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 efficiently structured: first sentence states purpose, second explains the oracle's dynamic nature, third describes the output and limitation, fourth lists use cases. No redundant sentences; every part earns its place. Information is front-loaded with the core function, making it easy for an agent to quickly parse.

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 no output schema, the description is remarkably complete. It covers what the tool does, how the data behaves (open-world), what the output is (boolean), and its limitation (no case detail). It also provides practical guidance (when to use). There are no obvious gaps 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 single parameter 'address' is fully described in the schema (EVM address format). The description adds little to parameter semantics—it reuses the same format but adds the screening purpose and use-case context. Since the schema already documents the parameter, the baseline of 3 applies; the description does not introduce new field-level meaning.

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 the exact function: 'Sanctions screening for a crypto wallet address' and names the specific oracle (Chainalysis) and coverage (OFAC SDN, EU, UN). It also states the output is a boolean, distinguishing it from sibling tools like screen_name (name-based) and verify_uk_company/verify_us_company (company verification), which are clearly different domains.

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 gives explicit use cases ('Use for AML compliance, counterparty due diligence, and payment screening before sending USDC or any funds to an address'). While it doesn't explicitly say 'do not use for name/company screening' or name alternatives, the purpose is so specific that an agent can infer when this tool applies versus siblings. It lacks an explicit when-not or alternative routing, but the context is strong enough.

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=true and openWorldHint=true. The description adds value by noting it is 'authoritative UK government open data' and specifying the returned data types (legal status, PSC, etc.). No contradiction with annotations, and the description enhances understanding of the tool's behavior.

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 five sentences, efficiently covering purpose, returned data, use cases, and authority. It is well-structured and front-loaded. Minor room for further conciseness, but overall very good.

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 tool's simplicity (1 parameter, no output schema), the description adequately lists the types of data returned (legal status, company type, incorporation date, address, PSC). It does not cover error handling or output format, but for a read-only lookup, it provides sufficient context.

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%, with the parameter companyNumber fully described. The description restates 'given a UK company registration number' but does not add significant new meaning beyond the schema's description and example. 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 clearly states it performs UK company verification and KYB lookup via Companies House, specifying the exact returned fields (legal status, type, incorporation date, address, PSC). It distinguishes itself from the sibling verify_us_company by being UK-specific and provides a distinct set of 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?

The description explicitly lists use cases: 'KYB onboarding, supplier and counterparty due diligence, and confirming a UK business is real, active, and who controls it.' It does not explicitly state when not to use, nor does it compare to siblings like screen_name or diligence, but the context is clear enough for an agent.

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=true and openWorldHint=true, and the description adds valuable behavioral detail: ambiguous name searches return candidates and never silently select a company. It also discloses the authoritative data source and the EDGAR coverage boundary, which go beyond what annotations convey.

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 compact and front-loaded: it states the core function, return fields, ambiguity behavior, scope boundary, and use case in a few ordered sentences. Every sentence adds useful information without 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?

With a single parameter and no output schema, the description does the necessary work: it enumerates the returned fields, explains behavior on ambiguous input, and constrains scope. An agent would know what to pass and what to expect from the result.

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% and the schema already explains that query is a ticker, CIK, or company name with examples. The tool description repeats this rather than adding new parameter-level meaning, so the baseline of 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 opens with a specific verb and resource: 'US public company verification via the SEC EDGAR system.' It clearly distinguishes itself from siblings like verify_uk_company by specifying US jurisdiction and public-company scope, and it enumerates concrete return fields such as CIK, SIC code, and listed exchanges.

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 states the intended use ('Use for KYB and counterparty due diligence on listed US entities') and explicitly defines when NOT to use it ('NOT private US companies, which register at the state level'). This gives an agent clear routing criteria relative to other tools.

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