Skip to main content
Glama

pick

Read-only

Raycasts screen points into the scene to report the hit instance, nearest Model ancestor, world position, normal, distance, and part CFrame/size/orientation for object identification or path tracing.

Instructions

Raycast from a screen point into the scene and report what's under it: the hit instance (+ nearest Model ancestor), world position, surface normal, distance, and the part's CFrame/size/orientation. Give x,y in pixels OR nx,ny in 0..1 OR nothing for the viewport center. Powers "what is that?" and tracing (sample points along a screen path). Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pick"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoscreen X in pixels
yNoscreen Y in pixels
nxNonormalized X 0..1 (used if x/y omitted)
nyNonormalized Y 0..1
onlyNowhitelist: only hit these instances/descendants
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.
rangeNoray length in studs (default 5000)
ignoreNoinstance paths to ignore (and their descendants)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the 'Read-only' sentence is largely redundant. What the description does add is the return payload shape (hit instance, nearest Model ancestor, position, normal, distance, CFrame/size/orientation), which is real value given there is no output schema, but it does not say what happens on a miss or how occlusion/transparent parts are treated. That is a meaningful behavioral gap for a raycast tool.

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 front-loaded with the core action and return values, then the coordinate modes, then use cases. It is dense but appropriately sized for an eight-parameter tool. The trailing 'Read-only' repeats the annotation and could be dropped, but the rest earns its place.

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?

With no output schema, the description does the important work of enumerating what is returned, and the schema fully covers the eight inputs. The main missing piece is the miss case: an agent cannot tell whether a failed raycast returns null, an empty result, or an error, which matters for tracing workflows that sample many points.

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 coverage is 100%, so all eight parameters are already documented individually. The description adds a cross-parameter rule — provide x,y in pixels OR nx,ny in 0..1 OR nothing for the viewport center — which is more than the schema states alone, but it does not explain 'only', 'ignore', or 'range' beyond what the schema already says.

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?

The description gives a precise verb and resource: raycast from a screen point and report the hit instance, ancestor Model, world position, normal, distance, and part CFrame/size/orientation. That is clearly distinguishable from siblings like get_selection or get_tree, which do not perform screen-space picking.

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?

It states concrete use cases ('what is that?' queries and sampling points along a screen path), which tells an agent when the tool is appropriate, and the input modes are explained. It does not name alternatives or say when not to use it, so it stops short of full routing guidance.

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