Skip to main content
Glama

Soxoa Automation Planning

Build a workflow pilot

build_workflow_pilot
Read-onlyIdempotent

Builds a pilot plan for one workflow, typically the first one prioritize_automation_workflows recommends, from 11 caller-supplied facts. Returns pilot steps, review gates, acceptance checks and a Markdown plan. It does not connect accounts, start provider work, store a plan, send messages or execute the workflow.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workflowName": "<workflowName>",
      "trigger": "<trigger>",
      "inputDescription": "<inputDescription>",
      "desiredOutput": "<desiredOutput>",
      "sourceSystem": "<sourceSystem>",
      "destinationSystem": "<destinationSystem>",
      "currentSteps": "<currentSteps>",
      "reviewOwner": "<reviewOwner>",
      "riskLevel": "<riskLevel>",
      "sensitiveData": "<sensitiveData>",
      "successChecks": "<successChecks>"
    },
    "name": "build_workflow_pilot"
  }
}

Input Schema

NameRequiredDescriptionDefault
triggerYesWhat starts the workflow, e.g. 'a supplier invoice email arrives'.
riskLevelYesCost of a wrong output: low, medium or high, as the user judges it.
constraintsNoLimits the plan must respect. Optional.
reviewOwnerYesPerson or role who approves drafts before they are used.
currentStepsYesToday's steps in order, 1 to 8, in the user's words.
sourceSystemYesSystem the inputs come from, e.g. Gmail.
workflowNameYesShort name of the workflow, as the user calls it.
desiredOutputYesThe result the user wants at the end.
sensitiveDataYesTrue if the inputs include personal, financial, health or confidential data.
successChecksYes1 to 6 checks that show the pilot worked, from the user.
inputDescriptionYesThe inputs the workflow reads, as the user describes them.
destinationSystemYesSystem the approved result goes to, e.g. QuickBooks.
systemsAlreadyUsedNoOther tools the team already uses. Optional.

Output Schema

NameRequiredDescriptionDefault
stepsYes
toolsYes
statusYes
rolloutYes
unresolvedYes
limitationsYes
reviewGatesYes
workflowNameYes
pilotMarkdownYes
suppliedFactsYes
recommendationYes
acceptanceChecksYes
readyToUsePromptYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed26 schema fields changed
    • addedInput schema / properties / constraints / description
      Added value: +"Limits the plan must respect. Optional."
    • addedInput schema / properties / currentSteps / description
      Added value: +"Today's steps in order, 1 to 8, in the user's words."
    • addedInput schema / properties / desiredOutput / description
      Added value: +"The result the user wants at the end."
    • addedInput schema / properties / destinationSystem / description
      Added value: +"System the approved result goes to, e.g. QuickBooks."
    • addedInput schema / properties / inputDescription / description
      Added value: +"The inputs the workflow reads, as the user describes them."
    • addedInput schema / properties / reviewOwner / description
      Added value: +"Person or role who approves drafts before they are used."
    • addedInput schema / properties / riskLevel / description
      Added value: +"Cost of a wrong output: low, medium or high, as the user judges it."
    • addedInput schema / properties / sensitiveData / description
      Added value: +"True if the inputs include personal, financial, health or confidential data."
    • addedInput schema / properties / sourceSystem / description
      Added value: +"System the inputs come from, e.g. Gmail."
    • addedInput schema / properties / successChecks / description
      Added value: +"1 to 6 checks that show the pilot worked, from the user."
    • addedInput schema / properties / systemsAlreadyUsed / description
      Added value: +"Other tools the team already uses. Optional."
    • addedInput schema / properties / trigger / description
      Added value: +"What starts the workflow, e.g. 'a supplier invoice email arrives'."
    • addedInput schema / properties / workflowName / description
      Added value: +"Short name of the workflow, as the user calls it."
    • addedOutput schema / properties / suppliedFacts / properties / constraints / description
      Added value: +"Limits the plan must respect. Optional."
    • addedOutput schema / properties / suppliedFacts / properties / currentSteps / description
      Added value: +"Today's steps in order, 1 to 8, in the user's words."
    • addedOutput schema / properties / suppliedFacts / properties / desiredOutput / description
      Added value: +"The result the user wants at the end."
    • addedOutput schema / properties / suppliedFacts / properties / destinationSystem / description
      Added value: +"System the approved result goes to, e.g. QuickBooks."
    • addedOutput schema / properties / suppliedFacts / properties / inputDescription / description
      Added value: +"The inputs the workflow reads, as the user describes them."
    • addedOutput schema / properties / suppliedFacts / properties / reviewOwner / description
      Added value: +"Person or role who approves drafts before they are used."
    • addedOutput schema / properties / suppliedFacts / properties / riskLevel / description
      Added value: +"Cost of a wrong output: low, medium or high, as the user judges it."
    • addedOutput schema / properties / suppliedFacts / properties / sensitiveData / description
      Added value: +"True if the inputs include personal, financial, health or confidential data."
    • addedOutput schema / properties / suppliedFacts / properties / sourceSystem / description
      Added value: +"System the inputs come from, e.g. Gmail."
    • addedOutput schema / properties / suppliedFacts / properties / successChecks / description
      Added value: +"1 to 6 checks that show the pilot worked, from the user."
    • addedOutput schema / properties / suppliedFacts / properties / systemsAlreadyUsed / description
      Added value: +"Other tools the team already uses. Optional."
    • addedOutput schema / properties / suppliedFacts / properties / trigger / description
      Added value: +"What starts the workflow, e.g. 'a supplier invoice email arrives'."
    • addedOutput schema / properties / suppliedFacts / properties / workflowName / description
      Added value: +"Short name of the workflow, as the user calls it."
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive behavior, and the description reinforces this with concrete non-actions: no account connection, no provider work, no storage, no messages, no execution. It also previews outputs (pilot steps, review gates, acceptance checks, Markdown plan). It adds real value beyond the annotations but does not discuss limits such as validation failures or how incomplete facts are handled.

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?

Two front-loaded sentences with zero padding: first what it produces and from what, then explicit scope exclusions. Every clause earns its place and the exclusions are batched efficiently.

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?

With an output schema present, the description need not detail return values, and the exclusion list plus the input-count framing make the tool's boundaries clear. The one gap is that it does not explain how judgment inputs like riskLevel, sensitiveData or constraints shape the generated plan, which matters for a 13-parameter generative tool.

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 100% across 13 parameters, so the schema carries the per-field burden. The description still contributes meaning by stating the plan is built "from 11 caller-supplied facts," signalling that every required value must come from the user rather than be invented, which is guidance the schema alone does not convey.

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?

States a specific verb+resource ("Builds a pilot plan for one workflow") and quantifies the input surface ("from 11 caller-supplied facts"). It situates itself against a named sibling (prioritize_automation_workflows), so an agent can distinguish it from the other tools without opening the schema.

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?

Gives clear selection context: this is the pilot-building step, typically following prioritize_automation_workflows. The negative scope ("does not connect accounts, start provider work, store a plan, send messages or execute the workflow") implicitly rules out using it for execution or persistence. It stops short of explicitly routing to estimate_automation_roi, so it is strong but not a complete when/when-not map.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources