Skip to main content
Glama
vision-gesture-control

vision-gesture-control

by 1nc0gn30

vision_classify_gesture

Classifies 21 hand landmarks into gesture types such as open palm, fist, pinch, and thumbs up, with confidence scores, pinch metrics, and finger extension states.

Instructions

Classifies 21 3D/2D hand landmarks (MediaPipe format) into gesture types (e.g. open_palm, fist, pointing_up, peace_sign, pinch, thumbs_up, rock_on, ok_sign) with confidence score, pinch metrics, and individual finger extension states.

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": {
      "landmarks": "<landmarks>"
    },
    "name": "vision_classify_gesture"
  }
}

Input Schema

NameRequiredDescriptionDefault
landmarksYesArray of 21 3D/2D hand landmarks (dicts with x, y, z or nested coordinate arrays).
handednessNoHandedness label ('Right', 'Left', or 'Unknown').Right
confidence_thresholdNoMinimum confidence threshold (0.0 - 1.0).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.5.0

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It usefully reveals the return content (confidence score, pinch metrics, finger states) and the gesture vocabulary, but says nothing about what happens with malformed input, how confidence_threshold affects results, or whether handedness alters classification.

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?

A single front-loaded sentence with no filler. The core action leads, and the enumerated outputs and gesture examples earn their place by telling the agent what it gets back.

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 must convey return values, and it does so concisely (gesture label, confidence, pinch metrics, finger states). What remains thin is edge-case behavior and prerequisites, not the core contract.

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% and each parameter is documented, so the baseline applies. The description reinforces the MediaPipe landmark format and names the gesture output set, adding modest meaning but nothing beyond the schema about handedness or threshold behavior.

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?

States a specific verb and resource: classifies 21 hand landmarks into named gesture types, listing concrete outputs (confidence, pinch metrics, finger extension states). It is clearly distinct from siblings like vision_classify_face, though it never names an alternative explicitly.

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

Usage Guidelines2/5

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

No when-to-use, when-not-to-use, or prerequisite guidance. It implies the input must be 21 landmarks but never states requirements about landmark source or ordering, or when a caller should prefer another vision tool.

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