AI Business System Advisor

by io.github.tenkai2018

Assess Trust And Control Risks

assess_trust_control_risks

Read-onlyIdempotent

Reviews a proposed AI workflow for human review needs, data boundaries, quality controls, escalation triggers, unsafe automation risks, and confidence.

Input Schema

TableJSON Schema

Name	Required	Description
`aiIdea`	No	Specific AI or automation idea the user is considering.
`businessType`	No	Type of business being reviewed.
`riskConcerns`	No	Known concerns about customer trust, brand risk, compliance, money, privacy, or quality control.
`workflowIdea`	No	AI workflow or agent idea to assess for trust and control risk.
`canAffectMoney`	No	Whether the workflow can influence pricing, refunds, payments, scope, or financial decisions.
`currentProblem`	No	Main business or workflow problem the user wants to solve.
`customerFacing`	No	Whether the workflow directly affects customers or customer-facing messages.
`currentControls`	No	Existing review, approval, QA, escalation, or monitoring controls.
`currentWorkflow`	No	Current workflow before AI or automation.
`proposedWorkflow`	No	Proposed workflow design, including what AI would do and what humans would review.
`usesSensitiveData`	No	Whether the workflow may use private, regulated, or sensitive business/customer data.
`canAffectBrandTrust`	No	Whether the workflow can affect brand reputation, customer expectations, or public trust.
`requiresExpertJudgment`	No	Whether the workflow needs professional, strategic, legal, financial, HR, or domain judgment.

Output Schema

TableJSON Schema

Name	Required	Description
`riskLevel`	Yes	Estimated risk level for the workflow or recommendation.
`confidence`	Yes	Confidence level based on the clarity and completeness of the provided business context.
`riskSummary`	Yes	Concise public-safe summary of the main trust and control risks.
`humanReviewRules`	Yes	Rules for when a human must review, approve, or override AI output.
`requiredControls`	Yes	Controls needed before the workflow should be piloted or expanded.
`escalationTriggers`	Yes	Conditions that should escalate to a human owner or expert reviewer.
`missingInformation`	Yes	Information the user should provide to improve risk assessment confidence.
`dataBoundaryWarnings`	Yes	Warnings about sensitive data, privacy, access boundaries, or inappropriate inputs.
`notRecommendedActions`	Yes	Actions that should not be automated in the current version.

Schema Changelog

Changes observed during successful MCP inspections.

Changed22 schema fields changedJul 27, 2026

addedInput schema / properties / aiIdea / description

Added value: +"Specific AI or automation idea the user is considering."

addedInput schema / properties / businessType / description
```
Added value: +"Type of business being reviewed."
```

addedInput schema / properties / canAffectBrandTrust / description

Added value: +"Whether the workflow can affect brand reputation, customer expectations, or public trust."

addedInput schema / properties / canAffectMoney / description

Added value: +"Whether the workflow can influence pricing, refunds, payments, scope, or financial decisions."

addedInput schema / properties / currentControls / description

Added value: +"Existing review, approval, QA, escalation, or monitoring controls."

addedInput schema / properties / currentProblem / description

Added value: +"Main business or workflow problem the user wants to solve."

addedInput schema / properties / currentWorkflow / description
```
Added value: +"Current workflow before AI or automation."
```

addedInput schema / properties / customerFacing / description

Added value: +"Whether the workflow directly affects customers or customer-facing messages."

addedInput schema / properties / proposedWorkflow / description

Added value: +"Proposed workflow design, including what AI would do and what humans would review."

addedInput schema / properties / requiresExpertJudgment / description

Added value: +"Whether the workflow needs professional, strategic, legal, financial, HR, or domain judgment."

addedInput schema / properties / riskConcerns / description

Added value: +"Known concerns about customer trust, brand risk, compliance, money, privacy, or quality control."

addedInput schema / properties / usesSensitiveData / description

Added value: +"Whether the workflow may use private, regulated, or sensitive business/customer data."

addedInput schema / properties / workflowIdea / description

Added value: +"AI workflow or agent idea to assess for trust and control risk."

addedOutput schema / properties / confidence / description

Added value: +"Confidence level based on the clarity and completeness of the provided business context."

addedOutput schema / properties / dataBoundaryWarnings / description

Added value: +"Warnings about sensitive data, privacy, access boundaries, or inappropriate inputs."

addedOutput schema / properties / escalationTriggers / description

Added value: +"Conditions that should escalate to a human owner or expert reviewer."

addedOutput schema / properties / humanReviewRules / description

Added value: +"Rules for when a human must review, approve, or override AI output."

addedOutput schema / properties / missingInformation / description

Added value: +"Information the user should provide to improve risk assessment confidence."

addedOutput schema / properties / notRecommendedActions / description

Added value: +"Actions that should not be automated in the current version."

addedOutput schema / properties / requiredControls / description

Added value: +"Controls needed before the workflow should be piloted or expanded."

addedOutput schema / properties / riskLevel / description

Added value: +"Estimated risk level for the workflow or recommendation."

addedOutput schema / properties / riskSummary / description

Added value: +"Concise public-safe summary of the main trust and control risks."

First observedMay 30, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and not destructive, so the description's job is to add context. It adds value by specifying the aspects reviewed (human review, data boundaries, etc.), which goes beyond the annotations. 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 a single sentence that conveys the core functionality without unnecessary words. While it is thorough, it could be slightly more concise by removing 'and confidence' at the end, but overall it is well-structured and front-loaded.

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 13 parameters (all optional) and the existence of an output schema, the description provides adequate coverage of the tool's purpose. It covers the key aspects of the review but does not detail the output structure, which is acceptable since the output schema exists.

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?

Schema coverage is 100% with well-described parameters. The description does not repeat parameter details or add additional meaning beyond what the schema provides. Baseline score of 3 is appropriate since the schema handles parameter documentation.

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 reviews a proposed AI workflow for specific aspects like human review needs, data boundaries, and quality controls, using a specific verb ('reviews') and resource ('proposed AI workflow'). It distinguishes from sibling tools like 'evaluate_ai_opportunities' by focusing on trust and control risks.

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

Usage Guidelines3/5

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

The description implies the tool should be used when there is a proposed AI workflow to assess risks, but it lacks explicit guidance on when not to use it or how it compares to alternatives like 'identify_bottlenecks' or 'evaluate_ai_opportunities'. No exclusion criteria or context triggers are provided.

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

All AI Business System Advisor tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.