Skip to main content
Glama

Group an existing workspace into zones

infer_zones
Destructive

Groups an existing workspace's flows into inferred labelled zones and moves blocks into them; previews changes first unless confirm=true.

Instructions

Reads a workspace's paths, static files and block types, groups its flows into labelled areas and LAYS THE BLOCKS OUT inside them. For a workspace built before zones existed — otherwise the biggest applications, the ones with the most to gain, stay the ones that look the most disorganised. It MOVES blocks, which is the point; nothing else changes (no block is created, deleted or edited, the links and code files are untouched), and every zone it produces is an ordinary one the user can rename, recolour or delete. Requires confirm=true — call without it first to see what it proposes. For a workspace you are BUILDING, pass zones to set_workspace_content/add_to_workspace instead: you know what the areas are, this has to guess.

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": {
      "workspaceId": "<workspaceId>"
    },
    "name": "infer_zones"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoMust be true to move the blocks. Omit/false previews only.
workspaceIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond destructiveHint=true by defining what is actually mutated: blocks are moved and re-parented into zones, while no block is created, deleted or edited and links/code files are untouched. It also notes generated zones are ordinary and user-editable. It does not describe the shape of the preview response, which is the main residual gap.

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 core behaviour and constraints are front-loaded and every clause carries information. The mid-sentence aside about the biggest applications looking disorganised is persuasive padding and the capitalised emphasis is stylistically noisy, but neither obscures the operative instructions.

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?

For a two-parameter mutation tool with no output schema, it covers the safety profile, the preview-first pattern, the alternative tools and the scope of mutation. What it leaves thin is the preview payload, so an agent knows a dry run exists but not precisely what it returns.

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?

The `confirm` schema entry already explains the preview behaviour, so the description's restatement is partly redundant, but it adds the workflow guidance of calling without it first. The required `workspaceId` has no schema description and the description never clarifies what a workspace ID is or how it is obtained, which is a mild gap at 50% coverage.

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?

Names a specific verb and resource chain: reads paths/static files/block types, groups flows into labelled zones, and lays blocks out inside them. It is immediately distinguishable from creation-oriented siblings, and the closing clause explicitly contrasts it with set_workspace_content/add_to_workspace.

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?

States exactly when to use it (a workspace built before zones existed) and when not to (a workspace you are building, where you already know the areas), naming the concrete alternatives to pass `zones` to instead. The two-step call pattern (call without confirm first for a preview) is also spelled out.

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