Server Quality Checklist

Tool Scores

• predict_risk_neuralA
  4.1/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and delivers thorough transparency: it declares read-only, stateless, idempotent behavior, rate limits, authentication needs, error handling, and data privacy. 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear sections, front-loading purpose and behavior. It is relatively long but every sentence adds value, so it earns its length.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has 9 parameters, no output schema, and no annotations, the description covers all necessary aspects: behavior, usage, limitations, and error handling. It is complete enough for an AI agent to select and invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description adds no information about any of the 9 parameters, despite 0% schema coverage. The schema's titles are self-explanatory, but the description fails to provide any additional context or clarify expected formats or values.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool provides neural network-based risk prediction for compliance checks. It is specific about verb ('predicts') and resource ('risk'), but does not explicitly differentiate from sibling tools like 'assess_ai_risk' or 'quick_scan'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description includes explicit 'When to use' and 'When NOT to use' sections, providing clear guidance on appropriate contexts and a crucial limitation about not substituting for legal counsel.

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

• create_certification_checklistA
  4.3/5.0
  Behavior5/5

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

  Since no annotations are provided, the description fully covers behavioral traits: read-only, no side effects, authentication requirements, rate limits, error handling, idempotency, and data privacy. This is thorough and exceeds typical disclosure.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Description is well-structured with clear sections, but some redundancy exists between 'Behavior' and 'Behavioral Transparency'. The length is justified by the amount of information, but minor trimming could improve conciseness.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the lack of output schema and annotations, the description covers purpose, parameters, behavior, and usage guidance. However, it misses the 'api_key' parameter and does not specify the exact output format beyond 'pass/fail status per item'.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The 'Args' section describes 5 of 6 parameters, adding meaning beyond the schema (0% coverage). However, it omits the 'api_key' parameter entirely, and does not explain constraints like date format or valid tier values.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description explicitly states 'Generate ISO 42001 certification readiness checklist with pass/fail', giving a clear verb, resource, and outcome. It distinguishes from siblings like 'assess_ai_risk' by focusing on checklist creation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Has dedicated 'When to use' and 'When NOT to use' sections, providing context for gap analysis and compliance verification. However, it does not explicitly compare with sibling tools like 'certification_timeline' or 'audit_management_system'.

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

• generate_policy_templateA
  4.4/5.0
  Behavior5/5

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

  With no annotations, the description fully bears the burden and delivers a comprehensive 'Behavioral Transparency' section covering side effects, authentication, rate limits, error handling, idempotency, and data privacy. This exceeds expectations.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is lengthy with some redundancy between 'Behavior' and 'Behavioral Transparency' sections. While structured, it could be more streamlined without losing clarity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  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 type and includes essential behavioral context. It covers parameters, use cases, and constraints, but missing api_key parameter weakens completeness slightly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, requiring compensation. The description's 'Args' section explains 5 of 6 parameters, adding meaning. However, 'api_key' is missing from that section, and default values or enums are not described, leaving a gap.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool generates AI policy documents per ISO 42021 requirements, listing specific clauses and components. It distinctively positions itself among siblings like 'assess_ai_risk' and 'audit_management_system' by focusing on policy template generation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description includes 'When to use' and 'When NOT to use' sections, providing clear guidance. However, the 'When to use' is somewhat generic and could be interpreted for multiple sibling tools, lacking explicit differentiation or alternative suggestions.

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

• audit_management_systemA
  4.5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and delivers extensively. It dedicates a 'Behavioral Transparency' section covering side effects (none, read-only), authentication (none for basic, API key for pro/enterprise), rate limits (10/day free, unlimited pro), error handling (structured errors), idempotency (fully idempotent), and data privacy (no storage or transmission). This is comprehensive and beyond typical disclosure.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear headers (Args, Returns, Behavior, When to use, etc.), but there is redundancy: the 'Behavior:' section and later 'Behavioral Transparency:' section repeat similar information. It is informative and front-loaded, but slightly longer than necessary.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has 6 parameters, no annotations, and no output schema, the description covers most aspects: purpose, usage, behavior, param semantics, and return format (clause-by-clause results). It lacks explicit detail on the exact structure of the return value but provides enough for an AI agent to understand expectations. Very close to complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%, so description must add meaning. It describes 5 of 6 parameters in the 'Args' section (missing 'api_key' parameter) with clear explanations (e.g., tier explained as 'free' or 'pro'). The description adds context not in schema. However, missing the api_key parameter and the slight confusion about passing it via environment variable vs parameter prevents a perfect score.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description starts with a clear verb+resource: 'Audit an AI management system against ISO/IEC 42001 clauses 4-10.' It specifies the scope (clauses 4-10) and what is returned (per-clause assessment, gap analysis, recommendations). This clearly distinguishes it from sibling tools like 'assess_ai_risk' or 'crosswalk_to_eu_ai_act' which have different purposes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description includes explicit 'When to use' and 'When NOT to use' sections, stating ideal use cases (gap analysis, readiness checks) and an important exclusion (not a substitute for legal counsel). It provides clear context but does not explicitly name or differentiate from sibling tools, which would push it to a 5.

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

• neural_insightsA
  4.6/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavioral traits: read-only, stateless, idempotent, rate limits, authentication requirements, error handling, and data privacy commitments. All relevant aspects are covered comprehensively.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear sections and front-loaded purpose. However, it is somewhat verbose, repeating read-only and idempotency details in the Behavioral Transparency section that could be condensed without losing clarity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool has only one parameter, no output schema, and no annotations, the description covers all necessary aspects: behavior, usage guidelines, side effects, authentication, and error handling. It is complete for the context.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The sole parameter 'api_key' is not explicitly described in the input schema (0% coverage). The description indirectly explains its usage via authentication details (basic usage no key, tiers require key), but does not directly map the parameter to its role or format.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: 'Get aggregate learning insights from the neural compliance model.' It uses a specific verb+resource combination and distinguishes itself from sibling tools like 'assess_ai_risk' and 'audit_management_system' by focusing on aggregate insights.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit 'When to use' and 'When NOT to use' sections. It recommends using the tool for compliance assessment, gap analysis, and documentation, and warns against using it as a substitute for legal counsel.

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

• assess_ai_riskA
  4.7/5.0
  Behavior5/5

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

  Despite no annotations, the description includes a comprehensive 'Behavioral Transparency' section covering side effects (read-only, no side effects), authentication (none for basic, API key for pro), rate limits (free 10/day, pro unlimited), error handling (structured errors), idempotency, and data privacy. This fully informs the agent 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear sections (When to use, Behavioral Transparency). However, it contains repetition: the 'Behavior' paragraph and 'Behavioral Transparency' section both state read-only and stateless. This redundancy slightly reduces conciseness.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description covers the tool's purpose, parameters, behavioral traits, and constraints extensively. It lacks precise output format details (e.g., expected JSON structure) but given no output schema, the general description is adequate. Missing api_key parameter description is a gap, but overall completeness is high.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description's Args section adds meaning for 5 of 6 parameters (system_description, system_name, risk_criteria, caller, tier), clarifying their roles. However, it omits the api_key parameter present in the schema. Given 0% schema coverage, the description partially compensates but misses one parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description explicitly states 'Perform ISO 42001 Annex B risk assessment for AI systems' and lists specific activities (risk criteria establishment, identification, analysis, evaluation). It clearly distinguishes from sibling tools like quick_scan or predict_risk_neural by focusing on comprehensive Annex B risk assessment.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides a dedicated 'When to use' section listing use cases (assess, audit, verify compliance, gap analysis) and a 'When NOT to use' warning against substituting for legal counsel. This gives clear guidance on appropriate contexts.

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

• quick_scanA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and excels. Includes details on side effects (read-only, no state changes), authentication (none required for basic), rate limits (10/day free), error handling (structured errors), idempotency, and data privacy. Covers all critical 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Well-structured with sections ('When to use', 'Behavioral Transparency', etc.), front-loaded with the key purpose. Some redundancy (behavioral points repeated in both 'Behavior' and 'Behavioral Transparency' sections), but overall efficient and easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Comprehensive for a simple tool with one input and no output schema. Details return value ('instant gap assessment'), behavior, authentication, rate limits, and error handling. Leaves no major gaps for an agent to infer.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Only one parameter 'description' with 0% schema coverage. The description provides a clear example and explanation ('e.g., customer service chatbot using GPT-4'), adding significant meaning beyond the bare schema. Fully compensates for the lack of schema documentation.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Clearly states the tool performs an ISO 42001 gap assessment using a system description. Verb and resource are specific. While sibling tools exist (e.g., assess_ai_risk, audit_management_system), the description does not explicitly differentiate, but the purpose is distinct enough.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit 'When to use' and 'When NOT to use' sections. Provides clear context for appropriate usage (gap analysis, readiness checks) and warns against substituting for legal advice. No explicit alternatives, but guidance is thorough.

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

• check_annex_controlsA
  4.8/5.0
  Behavior5/5

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

  Despite no annotations, the description includes a comprehensive 'Behavioral Transparency' section covering side effects (read-only, no side effects), authentication, rate limits, error handling, idempotency, and data privacy. No contradiction 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with clear sections and front-loaded purpose. However, there is slight redundancy between the 'Behavior:' and 'Behavioral Transparency:' sections, making it a bit longer than necessary.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 6 parameters, no output schema, and no annotations, the description is very complete, covering behavior, usage, parameters, and error handling. Missing a more detailed return format, but acceptable given the complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 0%, but the description's 'Args:' section explains each parameter in detail (e.g., 'implemented_controls: free text or comma-separated control IDs'), fully compensating for the missing schema descriptions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's purpose: evaluate AI system against ISO 42001 Annex A controls, mapping controls, assessing applicability, and producing a gap analysis. It distinguishes itself from siblings like 'assess_ai_risk' by focusing on a specific standard.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit 'When to use' and 'When NOT to use' sections provide clear guidance: use for compliance assessment, gap analysis, and documentation; not a substitute for legal advice. This helps the agent decide when to invoke.

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

• crosswalk_to_eu_ai_actA
  4.8/5.0
  Behavior5/5

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

  No annotations provided, so description fully covers behavior: read-only, stateless, idempotent, rate limits (free 10/day, pro unlimited), authentication (none for basic, API key for pro), error handling, and data privacy. All traits are accurately stated.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Well-organized with clear sections (Args, Returns, Behavior, When to use/not, Behavioral Transparency). Front-loaded with purpose. Some redundancy between Behavior and Behavioral Transparency sections could be trimmed.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With 5 parameters, no output schema, and no annotations, the description covers all necessary aspects: parameter details, return value with alignment ratings, rate limits, authentication, idempotency. No gaps were identified.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema has 0% description coverage, but the description's Args section explains iso_clauses, focus_area, caller, and tier with examples and constraints. However, the api_key parameter is in the schema but not described in Args, though mentioned later in authentication context.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool maps ISO/IEC 42001 to EU AI Act articles, a specific verb and resources. It distinguishes itself from sibling tools like risk assessment or audit by calling it a 'killer feature' for regulation-to-regulation mapping.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description includes explicit 'When to use' and 'When NOT to use' sections, providing clear guidance on appropriate contexts (gap analysis, compliance docs) and cautioning against legal advice substitution.

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

• certification_timelineA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description fully covers behavioral details: read-only, stateless, no side effects, idempotent, rate limits (free 10/day, pro unlimited), authentication (none for basic, API key for pro/enterprise), error handling, and data privacy. This exceeds the required transparency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is well-structured with sections and bullet points, but it is slightly verbose, containing more detail than strictly necessary. However, it front-loads the purpose and provides organized information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no output schema and no annotations, the description is complete: it covers purpose, usage guidelines, behavioral transparency, and parameter semantics thoroughly, leaving no gaps for a tool with no parameters.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters, and the schema coverage is 100% (empty). The description adds meaning by explaining the output (certification steps and timelines) and the nature of the tool, going beyond the baseline of 4 for zero-parameter tools.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool returns ISO 42001 certification steps and typical timelines. The verb 'returns' and the resource 'certification steps and timelines' are specific, and the tool is distinct from siblings like audit_management_system or check_annex_controls.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit 'When to use' (assess, audit, gap analysis, compliance documentation) and 'When NOT to use' (not a substitute for legal counsel) guidelines, offering clear context and exclusions.

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