Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Show an interactive 3D view (MCP App)

view_3d
Read-only

Display an interactive three.js 3D viewer to rotate, zoom, and click shapes (knot, sphere, gear, GLB sample), set the camera, highlight parts, and return user selections as context.

Instructions

Show an interactive 3D viewer (MCP App, three.js) the user can rotate, zoom and click. Shapes: knot, sphere, gear, glb-sample (glb-sample is a small glTF model read from test://models/sample.glb). Optionally set the camera and highlight one part. When the user selects a part it reaches you as model context or a chat message; view_3d_state reads the latest selection.

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": "view_3d"
  }
}

Input Schema

NameRequiredDescriptionDefault
shapeNoWhat to show (default knot)
cameraNoInitial camera; coordinates in [-100, 100]. Default position [5, 3.5, 6], target [0, 1.2, 0]
highlightNoName of a part to highlight (see parts in the result)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds the substantive behavior — the view is interactive (user can rotate/zoom/click), selections are delivered back asynchronously via model context or chat, and glb-sample loads from test://models/sample.glb. What's missing is whether the call returns immediately or blocks on user interaction, and what the result payload contains.

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?

Three front-loaded sentences with no filler; the capability comes first, then the shape vocabulary, then the selection feedback loop. The nested parenthetical about the glb path is slightly dense but still earns its place by disambiguating an otherwise cryptic enum value.

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 and full schema coverage, the description covers what an agent needs to invoke it: content choice, optional camera/highlight, and how selections come back. The remaining gap is the return payload — the highlight param says 'see parts in the result' without describing that structure, though view_3d_state partly compensates.

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, but the description earns a bump by explaining that glb-sample is a small glTF model read from test://models/sample.glb and by noting 'highlight one part' (a single value, not a list). It does not elaborate on camera coordinate conventions beyond what the schema already states.

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?

Specific verb and resource — 'Show an interactive 3D viewer (MCP App, three.js)' — plus the interaction model (rotate, zoom, click) and the concrete content options (knot, sphere, gear, glb-sample). It also routes the read-back path to the sibling view_3d_state, so an agent can separate rendering from state retrieval without opening either schema.

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?

Clear context for use: render a shape for the user and optionally seed camera/highlight, with an explicit statement that user selections arrive as model context or chat and that view_3d_state reads the latest selection. It stops short of saying when to choose this over view_3d_select or when not to render at all.

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