compliance-evidence

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

No annotations are provided, so the description carries full burden. It discloses key behavioral traits: grounding against 'CURRENT public gov facts', screening against federal exclusion lists, and running trap-fact refusals. It also clarifies the output is 'an EVIDENCE ARTIFACT with a hash-chain receipt — NOT a 'you are compliant' claim'. While it doesn't detail error handling or idempotency, it provides substantial transparency for an initial evaluation.

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 a single, dense paragraph that front-loads the main action and then explains the three key steps. Every sentence adds value without repetition or fluff. It is concise yet comprehensive for the tool's core functionality.

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 complexity (orchestrating grounding, screening, trap-facts) and the absence of an output schema, the description gives a good overview but lacks details on the exact structure of the EVIDENCE ARTIFACT, error scenarios, or prerequisites (e.g., need for API keys). It provides enough to understand what it does, but not enough to fully anticipate behavior.

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 baseline is 3. The description adds meaning beyond the schema: it explains that 'traps' are 'planted false facts refuted by live public data' and that 'entities' are screened against federal exclusion/sanctions lists (OFAC/LEIE/SAM). This enriches understanding of optional parameters, justifying a higher score.

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 builds a dated, source-linked, SIGNED compliance-evidence pack for regulated-AI deployers. It specifies the verb 'build', the resource (evidence pack), and differentiates from sibling tools like ground_claim, screen_entity, and verify_pack by encompassing multiple steps (grounding, screening, trap-facts) and producing an artifact.

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 provides context ('for a regulated-AI deployer to file with their auditor') but does not explicitly state when to use this tool versus alternatives such as ground_claim, screen_entity, or verify_pack. It implies usage for a complete pack, but lacks clarity on when to choose this over simpler tools.

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 effectively communicates the tool's behavior: it returns a dual-cited record if a contradiction exists, or a descriptive null otherwise. It also notes the response serves as audit evidence, providing useful context beyond a simple return type.

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 two sentences, but the first sentence contains jargon ('live contradiction-engine', 'dual-cited record') that may reduce clarity. Nonetheless, it avoids unnecessary information.

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 what the tool returns in both success and failure cases, but it omits details like error handling for invalid tickers, rate limits, or prerequisites. Given the tool's specialized nature, additional context would improve completeness.

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 'ticker' parameter is not described in the schema (0% coverage) and the description does not explain its meaning or format. While 'ticker' is somewhat self-explanatory as a stock ticker, the lack of explicit documentation forces the agent to infer its usage.

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 specifies the tool's action: 'Ground one public-company claim against CURRENT gov facts via the live contradiction-engine.' It uniquely identifies the resource (public-company claim) and distinguishes itself from siblings like 'screen_entity' by focusing on contradiction checking.

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 when verifying a public-company claim against government data, but it does not explicitly state when to use this tool versus alternatives like 'build_evidence_pack' or 'verify_pack', nor does it mention exclusions or prerequisites.

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 reveals that it screens via a 'live exclude-feed' and is 'FCRA-safe', but does not disclose behavioral aspects like whether it modifies state, requires authentication, or rate limits. It is a read-only lookup, but this is not explicitly stated.

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 a single, efficient sentence that front-loads the core action. However, it could be improved by splitting to cover parameter details or usage notes. It earns its place but sacrifices completeness for brevity.

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 and 4 parameters with 0% description coverage, the description is incomplete. It provides the list of databases and compliance note but fails to explain the function of optional parameters, return values, or error scenarios. The agent lacks essential context to 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 input schema has 4 parameters with 0% description coverage, yet the description only mentions 'name' implicitly via 'named entity'. It fails to explain the semantics of 'npi', 'uei', and 'state' – what they represent or how they affect the screening. This leaves the agent guessing about optional identifiers.

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 'Screen a named entity' and the specific resource: federal exclusion/sanctions lists (OFAC SDN, OFAC Consolidated, OIG LEIE; SAM where enabled). It distinguishes itself from consumer reports with 'FCRA-safe' and specifies it's for KYB/sanctions screening, making its purpose unambiguous.

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 does not explicitly state when to use this tool versus its siblings (build_evidence_pack, ground_claim, verify_pack). It implies usage for sanctions screening but provides no guidance on when not to use it or alternatives for different use cases like claims verification or evidence building.

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 states the tool verifies integrity via hash-chain receipt, suggesting a read-only operation, but does not disclose what happens on failure, authorization needs, or rate limits. Adequate but not comprehensive.

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 (one sentence) and front-loaded with the core purpose. It could be slightly restructured for clarity, but every part is relevant and 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?

For a simple one-parameter tool with no output schema or annotations, the description covers the core purpose and input. Missing details about return value or error handling, which for a verification tool might be useful, but overall adequate.

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?

With 0% schema description coverage and only one parameter, the description adds context ('Pass the pack id') beyond the schema's type-only definition. However, it lacks format specifics or examples, making it minimally sufficient.

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's purpose: verifying a pack's hash-chain receipt to prove the artifact is unaltered since generatedAt. It uses specific verb 'verify' and resource 'pack's hash-chain receipt', and distinguishes from siblings (build_evidence_pack, ground_claim, screen_entity) as a verification tool.

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 (pass the pack id) but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria or prerequisites. The context is clear but no guidance on when not to use.

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