Skip to main content
Glama
tenkai2018

ai-business-system-advisor-mcp

by tenkai2018

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
NameRequiredDescriptionDefault
notesNoAny additional context the user wants considered in the review.
offerNoCore product, service, package, or outcome the business sells.
risksNoKnown risks or control concerns that should shape the workflow design.
aiIdeaNoAI or automation idea the user is considering.
teamSizeNoApproximate team size and key roles involved in the workflow.
goal90DaysNoDesired business or workflow outcome over the next 90 days.
bottlenecksNoKnown or suspected bottlenecks the first workflow should address.
constraintsNoKnown constraints such as budget, team capacity, tools, timeline, compliance needs, or data access.
currentGoalNoCurrent business goal the user wants the review to support.
businessTypeNoType of business, such as ecommerce, SaaS, consulting, agency, local service, or solo business.
revenueModelNoHow the business earns revenue, such as projects, retainers, subscriptions, services, or products.
riskConcernsNoConcerns related to customer trust, brand reputation, legal exposure, sensitive data, or quality control.
opportunitiesNoAI opportunities already identified or under consideration.
currentProblemNoMain business or workflow problem the user wants to solve.
targetCustomerNoPrimary customer segment or buyer the business serves.
currentWorkflowNoHow the relevant workflow currently works, including manual steps, tools, handoffs, and review points.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
aiRoleYesWhat AI should observe, summarize, draft, classify, or prepare.
humanRoleYesWhat a human should approve, decide, handle, or monitor.
confidenceYesConfidence level based on the clarity and completeness of the provided business context.
reviewRuleYesRule for when human review is required before output or action.
escalationRuleYesRule for cases that should escalate to a human owner or expert.
successMetricsYesPractical metrics to evaluate workflow pilot success.
expectedOutcomeYesExpected business outcome if the workflow is piloted successfully.
whyThisWorkflowYesReason this workflow is a practical first candidate based on value, readiness, and risk.
workflowCategoryYesCategory of workflow, such as sales prep, support triage, QA, reporting, or operations.
missingInformationYesInformation the user should provide to improve workflow recommendation confidence.
recommendedWorkflowYesNarrow AI-human workflow recommended as the safest first implementation.
firstImplementationScopeYesSmallest practical pilot scope for the first version.
Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the tool is non-destructive and safe. The description adds value by detailing the components of the recommendation (roles, rules, metrics, missing info), which goes beyond what annotations provide.

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 is front-loaded with the core action. It is concise, but could be slightly more structured by, for example, listing the components in a bulleted fashion for readability.

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 large number of parameters (16) and the existence of an output schema, the description adequately covers what the tool does. It mentions that the recommendation includes specific components, which is sufficient for understanding the output. However, it could explicitly state that the recommendation is based on the provided input parameters.

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 description coverage is 100%, with each of the 16 parameters having a clear description. The tool description does not add additional semantics beyond what is already in the schema, so baseline score of 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?

The description clearly states that the tool recommends the 'safest narrow AI-human workflow to implement first' and specifies what the recommendation includes (roles, review rules, escalation rules, success metrics, missing information). This distinguishes it from siblings like 'recommend_next_step' which likely has a different scope.

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 usage for first workflow implementation but does not provide explicit guidance on when to use this tool versus alternatives such as 'analyze_business_context' or 'evaluate_ai_opportunities'. No exclusions or when-not-to-use cases are mentioned.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tenkai2018/ai-business-system-advisor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server