Skip to main content
Glama

Soxoa Automation Planning

Prioritize automation workflows

prioritize_automation_workflows
Read-onlyIdempotent

Ranks 1 to 12 caller-described workflows by value, predictability, judgment, data sensitivity and integration complexity, and labels each automate, assist or discovery. Each workflow requires a name, weekly hours, predictability, judgment required, error cost, data sensitivity and system count. Returns each workflow's score, recommendation, human-review flag and rationale, plus a recommended first workflow and guardrails. It does not connect to or change any system.

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": {
      "workflows": "<workflows>"
    },
    "name": "prioritize_automation_workflows"
  }
}

Input Schema

NameRequiredDescriptionDefault
workflowsYes

Output Schema

NameRequiredDescriptionDefault
guardrailsYes
rankedWorkflowsYes
recommendedFirstWorkflowYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / workflows / items / description
      Added value: +"One recurring workflow the user described. Ask for any field you lack."
    • addedInput schema / properties / workflows / items / properties / dataSensitivity / description
      Added value: +"How sensitive the data handled is."
    • addedInput schema / properties / workflows / items / properties / errorCost / description
      Added value: +"Cost of a mistake reaching a customer or record."
    • addedInput schema / properties / workflows / items / properties / judgmentRequired / description
      Added value: +"How much human judgment each case needs."
    • addedInput schema / properties / workflows / items / properties / name / description
      Added value: +"Workflow name, in the user's words."
    • addedInput schema / properties / workflows / items / properties / predictability / description
      Added value: +"How often the steps follow the same pattern."
    • addedInput schema / properties / workflows / items / properties / systemsCount / description
      Added value: +"Number of systems the workflow touches, 1 to 20."
    • addedInput schema / properties / workflows / items / properties / weeklyHours / description
      Added value: +"Total team hours per week spent on it, from the user."
  2. Changed2 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / workflows / items / additionalProperties
      Removed value: -false
  3. First observed

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, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is structured data. The description reinforces this with 'does not connect to or change any system' and discloses the 1-12 batch ceiling and that a human-review flag and guardrails come back, which goes modestly beyond the annotations. It still says nothing about determinism of the ranking, handling of duplicate workflows, or failure modes for malformed input.

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?

Three sentences, front-loaded with the ranking behavior, then the input contract, then the return payload and the no-side-effects guarantee. No filler and no repetition of the title.

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?

For a single-array read-only scoring tool, the definition covers scope, criteria, cardinality limits, required fields, return contents and side-effect guarantees; an output schema exists, so return values need no further prose. An agent has everything needed to call it correctly.

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?

Although the reported coverage metric is 0%, the description enumerates every required per-workflow field (name, weekly hours, predictability, judgment required, error cost, data sensitivity, system count) and frames them as caller-supplied facts the agent must collect ('Ask for any field you lack' appears in the schema). That adds framing the schema's per-property descriptions do not: all seven fields are mandatory and one object represents one recurring workflow.

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 names a specific verb and resource ('Ranks 1 to 12 caller-described workflows') plus the criteria used and the three output labels (automate, assist, discovery), so the tool's function is unmistakable. It separates itself from build_workflow_pilot implicitly via 'It does not connect to or change any system', but never names estimate_automation_roi or states the boundary explicitly.

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?

Usage is only implied: the phrasing suggests this is the triage/ranking step that would precede estimating ROI or building a pilot. There is no explicit 'use this when...' statement, no exclusion rules, and no prerequisites (e.g., that the user must already have described their workflows).

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