ai-business-system-advisor-mcp

by tenkai2018

Overview Schema Source Related Servers Discussions Admin

Recommend First Workflow

recommend_first_workflow

Read-onlyIdempotent

Recommends a safe narrow AI-human workflow to implement first, detailing roles, review and escalation rules, success metrics, and missing information.

Instructions

Recommends the safest narrow AI-human workflow to implement first, including roles, review rules, escalation rules, success metrics, and missing information.

Input Schema

TableJSON Schema

Name	Required	Description
`notes`	No	Any additional context the user wants considered in the review.
`offer`	No	Core product, service, package, or outcome the business sells.
`risks`	No	Known risks or control concerns that should shape the workflow design.
`aiIdea`	No	AI or automation idea the user is considering.
`teamSize`	No	Approximate team size and key roles involved in the workflow.
`goal90Days`	No	Desired business or workflow outcome over the next 90 days.
`bottlenecks`	No	Known or suspected bottlenecks the first workflow should address.
`constraints`	No	Known constraints such as budget, team capacity, tools, timeline, compliance needs, or data access.
`currentGoal`	No	Current business goal the user wants the review to support.
`businessType`	No	Type of business, such as ecommerce, SaaS, consulting, agency, local service, or solo business.
`revenueModel`	No	How the business earns revenue, such as projects, retainers, subscriptions, services, or products.
`riskConcerns`	No	Concerns related to customer trust, brand reputation, legal exposure, sensitive data, or quality control.
`opportunities`	No	AI opportunities already identified or under consideration.
`currentProblem`	No	Main business or workflow problem the user wants to solve.
`targetCustomer`	No	Primary customer segment or buyer the business serves.
`currentWorkflow`	No	How the relevant workflow currently works, including manual steps, tools, handoffs, and review points.

Output Schema

TableJSON Schema

Name	Required	Description
`aiRole`	Yes	What AI should observe, summarize, draft, classify, or prepare.
`humanRole`	Yes	What a human should approve, decide, handle, or monitor.
`confidence`	Yes	Confidence level based on the clarity and completeness of the provided business context.
`reviewRule`	Yes	Rule for when human review is required before output or action.
`escalationRule`	Yes	Rule for cases that should escalate to a human owner or expert.
`successMetrics`	Yes	Practical metrics to evaluate workflow pilot success.
`expectedOutcome`	Yes	Expected business outcome if the workflow is piloted successfully.
`whyThisWorkflow`	Yes	Reason this workflow is a practical first candidate based on value, readiness, and risk.
`workflowCategory`	Yes	Category of workflow, such as sales prep, support triage, QA, reporting, or operations.
`missingInformation`	Yes	Information the user should provide to improve workflow recommendation confidence.
`recommendedWorkflow`	Yes	Narrow AI-human workflow recommended as the safest first implementation.
`firstImplementationScope`	Yes	Smallest practical pilot scope for the first version.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.10Jul 30, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the description adds no new behavioral traits. It mentions 'safest' but does not contradict annotations.

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

Conciseness5/5

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

Single sentence, 18 words, front-loaded with action and resource. No wasted words; efficiently covers purpose and output elements.

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?

Adequate for a tool with output schema and full schema coverage. Could mention that all parameters are optional or highlight idempotency, but current description is sufficient.

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 descriptions for all 16 parameters. The description does not add meaning beyond the schema; baseline 3 is appropriate.

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?

Clearly states verb 'recommends', resource 'safest narrow AI-human workflow', and scope 'to implement first'. Lists included elements (roles, review rules, etc.), distinguishing it from siblings like recommend_next_step.

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?

Implies usage for prioritizing the first workflow but provides no explicit guidance on when to use versus alternatives like evaluate_ai_opportunities, or 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.

Deploy Server