Skip to main content
Glama

place_on

DestructiveIdempotent

Positions a Part or Model flush on a raycast surface using its bounding box to avoid clipping or floating; supports screen/top-target/ground modes, grid snap, normal alignment, and dry-run preview.

Instructions

Compute and apply an accurate placement: raycast to a surface (a screen point, a target instance's TOP via onTarget, or straight down via ground), then sit the object FLUSH on it — offset by the object's bounding box so it doesn't clip or float. Optional alignToNormal (rotate to the surface) and snap (grid studs). Use dryRun to get the computed CFrame without moving. Moves a Part (CFrame) or a Model (PivotTo, bbox-center flush). Write tool.

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": {
      "path": "<path>"
    },
    "name": "place_on"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoscreen X px (screen-ray mode)
yNoscreen Y px
nxNonormalized X 0..1
nyNonormalized Y 0..1
pathYesthe instance to place (BasePart or Model)
snapNosnap final X,Z to this grid (studs)
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
rangeNoray length (default 5000)
dryRunNocompute + return the CFrame without moving anything
groundNodrop straight down from the object's current X,Z onto whatever's below
ignoreNoextra instances the ray should ignore
onTargetNoplace on the TOP surface of this instance
extraOffsetNoextra gap above the surface (studs, default 0)
alignToNormalNorotate the object to sit flush on a sloped surface (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare the write/destructive/idempotent profile, and the description reinforces it ('Write tool') rather than contradicting it. It adds real behavioral detail beyond annotations: bounding-box offsetting to prevent clipping/floating, Model handled via PivotTo with bbox-center flush, and dryRun returning a CFrame without mutation. It stops short of describing limits or side effects on surrounding geometry.

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?

Front-loaded with the core action and dense with useful specifics; the em-dash asides carry real information rather than filler. It is a single run-on block, which slightly hurts scannability of the mode options.

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 14-parameter mutation tool with no output schema, the description covers the raycast modes, flush behavior, align/snap options, and the dryRun return. A few parameters and any failure behavior (e.g. when no surface is hit) are left unaddressed.

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%, so the baseline is 3; the description goes further by explaining how mode parameters interrelate (screen point vs onTarget vs ground) and what alignToNormal, snap, and dryRun change about the result. It does not cover every parameter (e.g. extraOffset, ignore, range) but the essentials for correct invocation are clarified.

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 chain (compute, raycast, flush-place) plus the resource types it moves (Part CFrame / Model PivotTo) and the three targeting modes. An agent knows immediately this is a surface-snapping placement tool, not a generic transform setter.

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 mode-selection context: screen point, onTarget for an instance's TOP, or ground for straight down, and tells the agent to use dryRun to preview. It lacks explicit when-not-to-use or a named sibling alternative, so it stops short of a 5.

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