Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Store a 3D view selection (app-only)

view_3d_select

Records the user's part selection or deselection in a 3D viewer, including the current camera, to keep selection state and viewpoint synchronized.

Instructions

Called by the 3D viewer when the user selects a part (or clears the selection), with the current camera. Hidden from the model.

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": {
      "viewId": "<viewId>",
      "part": "<part>"
    },
    "name": "view_3d_select"
  }
}

Input Schema

NameRequiredDescriptionDefault
partYes
cameraNo
viewIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the calling context, that the selection can be cleared (null part), and that camera state is transmitted. It leaves out what happens to stored state, whether prior selections are overwritten, and what the tool returns or errors on. Adequate but not rich for a state-storing mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the invocation trigger and ending with the audience constraint. Nothing is padded and no sentence is redundant.

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?

There is no output schema and no annotations, and the input schema is largely untyped, so the description is the only substantive documentation. It covers the trigger and the meaning of two of three fields but says nothing about persistence semantics, the role of viewId, or the result. Sufficient to recognize the tool, not sufficient to fully reason about it.

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 0% and the camera property is an untyped empty schema, so the description is doing real work: it explains that 'part' may be null on deselection and that 'camera' is the viewer's current camera. The third parameter, viewId, gets no explanation at all despite being required, which caps the score.

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 a concrete trigger and effect: it is invoked by the 3D viewer when the user selects or clears a part, and it captures the current camera along with the selection. That is a specific verb-plus-resource statement, and the 'hidden from the model' note separates it from the other view_3d siblings. It stops short of a fully self-contained purpose statement because the storage/return behavior is never described.

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?

The when-to-use condition is explicit: it fires on a user selection or deselection in the 3D viewer. The closing note that it is hidden from the model effectively tells an agent it is not a tool to call on its own initiative. No alternatives are named, so it is not a full 5.

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