Skip to main content
Glama

Plan Tool Workflow

plan_tool_workflow
Read-onlyIdempotent

Routes a raw user message to an appropriate tool workflow when none is preloaded, returning ordered tool names and sufficiency flags to guide next steps.

Instructions

Route a user message to the optimal tool workflow. Returns a plan object with the ordered tool names and sufficiency flags. Use when the server has not yet pre-injected a workflow plan for the current conversation. Pass userMessage from the raw user message; skip if a plan is already present in context.

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": {
      "userMessage": "<userMessage>"
    },
    "name": "plan_tool_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
userMessageYesThe raw user message to analyze

Output Schema

NameRequiredDescriptionDefault
needsResolveYes
needsSourcingNo
workflowStepsYes
confidenceNoteYes
detectedIntentYes
maxSearchCallsYes
needsSubstitutionsYes
detectedRestrictionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value beyond that by disclosing the output shape (ordered tool names plus sufficiency flags) and the precondition of a pre-injected plan, though it says nothing about latency, failure modes, or what an insufficient plan implies.

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?

Four short sentences, front-loaded with the action and return value before the usage conditions. Efficient overall; the closing 'skip if a plan is already present in context' partially restates the earlier 'has not yet pre-injected' clause rather than adding a new condition.

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?

An output schema exists, so the return value need not be explained in depth, yet the description still sketches it. With one fully documented parameter and annotations covering the safety profile, the definition tells an agent everything needed: what it does, when to call it, when not to, and what argument to pass.

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 coverage is 100% and there is a single required parameter, so the baseline is 3. The description nonetheless adds real meaning by specifying the value must come from the raw user message rather than a paraphrase or summary, which the schema's 'The raw user message to analyze' only partially conveys.

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 and resource: 'Route a user message to the optimal tool workflow', then names the return shape ('plan object with the ordered tool names and sufficiency flags'). This is clearly distinguishable from the domain siblings (plan_dish_research, generate_recipe, etc.), which operate on content rather than routing.

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

Usage Guidelines5/5

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

Gives an explicit positive trigger ('Use when the server has not yet pre-injected a workflow plan for the current conversation') and an explicit negative case ('skip if a plan is already present in context'). That is a complete when/when-not rule with no inference required from the agent.

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