Skip to main content
Glama

ai_modeling_segmentation_edit

Edit GLB model segmentation locally by selecting, brushing, painting, merging, splitting, renaming, and undoing or redoing segment labels to produce an updated model state.

Instructions

select, brush, paint, merge, split, rename, undo or redo segment labels locally

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": {
      "model_path": "<model_path>",
      "destination_path": "<destination_path>"
    },
    "name": "ai_modeling_segmentation_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsNoOrdered edit actions; empty creates the initial state.
model_pathYesOriginal static indexed GLB; never use a re-exported preview as the source.
project_idNoBind a new state to the Studio project; required before native saving.
state_pathNoPrevious segmentation state JSON; must match the exact source GLB.
reserved_namesNoNames reserved by project metadata (deleted/renamed/transformed parts).
source_metadataNoSource operator children_deleted, children_rename and children_transform_matrix; reused from state when omitted.
destination_pathYes
expected_operator_idNoSource operator from project-get; prevents applying stale edits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.4

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already establish that this is not read-only, is open-world, and is non-destructive. The description adds useful context by saying the edits happen locally and by listing supported operations, but it does not explain state chaining, destination writing, initial-state behavior, or what happens to the previous segmentation state.

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 tightly packed sentence with no filler, and the core action list is front-loaded. It is appropriately sized, though the comma-separated verb list is dense and could have used slight structural grouping around stateful edit actions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 8-parameter stateful editing tool, the description is very sparse: it does not explain ordered actions, initial state creation, state_path/destination_path chaining, or project binding. The rich schema descriptions and annotations compensate for much of that, but the overall definition still leaves the agent to infer the workflow from structured fields.

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 88%, so the schema already documents most parameters in detail. The description only lists action verbs and does not add meaning for model_path, state_path, destination_path, source_metadata, reserved_names, or expected_operator_id; it also omits the schema's pick and reset actions.

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 specific edit operations (select, brush, paint, merge, split, rename, undo/redo) and the target resource: segment labels. It clearly identifies an editing tool, though it omits the schema-supported actions pick and reset and does not explicitly distinguish itself from segmentation_inspect or segmentation_preview.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance or comparison to sibling tools. The single word 'locally' hints at scope but does not tell an agent when to edit versus inspect, preview, or prompt segmentation.

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

Deploy Server

Other Tools