Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

cut_qt_prepare_line_selection

Prepares a current whole native internal line for selection using an installed semantic selector, then returns a single-use selection_ref after native, PointInfo, and frame checks.

Instructions

Use an installed core-owned semantic selector for one current whole native internal line.

Live-verified profiles are an anchored straight line with an existing seam, and an anchored single cubic segment. Supply one line from cut_qt_inspect. The packaged atomic provider prepares a frame candidate without changing selection. A legacy installed selection provider may select the line during preparation. Returns a single-use selection_ref after fresh native, PointInfo and frame checks.

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": {
      "pattern_uuid": "<pattern_uuid>",
      "shape_uuid": "<shape_uuid>",
      "line_uuid": "<line_uuid>",
      "topology_fingerprint": "<topology_fingerprint>",
      "scene_token": "<scene_token>",
      "request_id": "<request_id>"
    },
    "name": "cut_qt_prepare_line_selection"
  }
}

Input Schema

NameRequiredDescriptionDefault
line_uuidYes
request_idYes
shape_uuidYes
scene_tokenYes
pattern_uuidYes
topology_fingerprintYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior4/5

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

With no annotations present, the description carries the full behavioral burden and does so unusually well: it discloses that the packaged atomic provider prepares a candidate 'without changing selection', warns that a legacy provider may mutate selection during preparation, and states the result is a single-use ref gated by fresh native, PointInfo and frame checks. What remains undisclosed is failure behavior and what invalidates or consumes the ref beyond 'single-use'.

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

Conciseness3/5

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

There is no filler, but the six telegraphic fragments are jargon-dense and read as internal notes rather than an introduction ('core-owned semantic selector', 'packaged atomic provider'). The actual purpose and return value are split across the first and last lines, weakening front-loading.

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

Completeness2/5

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

The behavioral and return-value side is reasonably covered, but for a six-parameter, no-annotation, no-output-schema tool operating on opaque tokens and fingerprints, the definition leaves an agent unable to populate five of six arguments or reason about error recovery. That is a substantive gap relative to the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six required parameters, so the description must compensate and largely does not. Only line_uuid is indirectly explained ('supply one line from cut_qt_inspect'); pattern_uuid, shape_uuid, topology_fingerprint, scene_token and request_id are opaque tokens whose provenance, format and freshness requirements are left entirely undefined.

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 the specific resource (one current whole native internal line) and the mechanism (an installed core-owned semantic selector), and the closing sentence reveals the actual output contract: a single-use selection_ref. It also implicitly differentiates from the inspect sibling by requiring input 'from cut_qt_inspect', though the verb 'prepare' is never stated as plainly as the title suggests.

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

Usage Guidelines3/5

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

'Supply one line from cut_qt_inspect' gives an explicit upstream prerequisite, and the sentence about live-verified profiles ('anchored straight line with an existing seam, and an anchored single cubic segment') constrains which inputs are supported. However, it never states when to choose this over the downstream execute/alternate cut tools, nor any exclusion conditions beyond the profile limitation.

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