Skip to main content
Glama

Digital Gemology: gemstone and diamond cut library

Cut Performance Index scores

get_cut_scores
Read-onlyIdempotent

Scores from the Digital Gemology Cut Performance Index for every cut we sell: overall, brilliance, fire, scintillation, tilt, symmetry, spread, shape-norm and leakage, ray traced separately in 26 gemstones (diamond, moissanite, cubic zirconia, ruby, sapphire, emerald, amethyst, topaz, spinel, demantoid, zircon, tourmaline, peridot, tanzanite, YAG, pyrope, almandine, spessartine, grossular, chrysoberyl, kunzite, iolite, morganite, GGG, strontium titanate and synthetic rutile), with each cut's place in its material. Filter by cut, category or material; with no filter, every row. Figures are unrounded. Never compare or rank scores across materials. Ruby and sapphire share one refractive index, so the same figures; material_notes lists the other stones that share figures and the doubling caveats. Cuts not yet scored come with the reason.

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": "get_cut_scores"
  }
}

Input Schema

NameRequiredDescriptionDefault
cutNoThe cut's slug or name, for example 'oval' or 'DG-M5'.
categoryNobrilliants, jewelry, historic, house or platonic.
materialNoOne stone, as its slug; leave it out for all 26. An alias stone returns the rows of the stone it shares optical constants with, and says so.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / material / description
      Previous value: -"One stone (diamond, moissanite, cubic-zirconia, ruby, sapphire, emerald or amethyst); leave it out for all seven."New value: +"One stone, as its slug; leave it out for all 26. An alias stone returns the rows of the stone it shares optical constants with, and says so."
    • changedInput schema / properties / material / enum
      Previous value: -[
      -  "diamond",
      -  "moissanite",
      -  "cubic-zirconia",
      -  "ruby",
      -  "sapphire",
      -  "emerald",
      -  "amethyst"
      -]New value: +[
      +  "diamond",
      +  "moissanite",
      +  "cubic-zirconia",
      +  "ruby",
      +  "sapphire",
      +  "emerald",
      +  "amethyst",
      +  "topaz",
      +  "spinel",
      +  "demantoid",
      +  "zircon",
      +  "tourmaline",
      +  "peridot",
      +  "tanzanite",
      +  "yag",
      +  "pyrope",
      +  "almandine",
      +  "spessartine",
      +  "grossular",
      +  "chrysoberyl",
      +  "kunzite",
      +  "iolite",
      +  "morganite",
      +  "ggg",
      +  "strontium-titanate",
      +  "synthetic-rutile",
      +  "aquamarine",
      +  "citrine",
      +  "quartz",
      +  "alexandrite"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / material / description
      Previous value: -"diamond or moissanite; leave it out for both."New value: +"One stone (diamond, moissanite, cubic-zirconia, ruby, sapphire, emerald or amethyst); leave it out for all seven."
    • changedInput schema / properties / material / enum
      Previous value: -[
      -  "diamond",
      -  "moissanite"
      -]New value: +[
      +  "diamond",
      +  "moissanite",
      +  "cubic-zirconia",
      +  "ruby",
      +  "sapphire",
      +  "emerald",
      +  "amethyst"
      +]
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent/destructive annotations by disclosing result semantics an agent could not guess: figures are unrounded, scores are not comparable across materials, ruby and sapphire share one refractive index and therefore identical figures, material_notes enumerates other stones that share figures plus doubling caveats, and unscored cuts return a reason. These are exactly the caveats that prevent misinterpretation of the returned data.

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?

The opening clause is well front-loaded, but the sentence then enumerates all 26 gemstone names, which duplicates the material enum in the schema verbatim and consumes most of the text. The critical constraints (no cross-material ranking, shared-index caveats) arrive at the end and are easy to skim past. Length is defensible for the caveats, not for the stone list.

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 carries the burden of describing returns and does so reasonably: it names the score dimensions, notes per-material placement for each cut, states that figures are unrounded, and explains the failure shape (unscored cuts come with a reason). It even names a response field, material_notes. What it lacks is any indication of result size or field naming beyond that single example.

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 adds genuine meaning on top: the no-filter case returns every row, and material aliases resolve to the rows of the stone sharing optical constants. It reinforces the three filter axes without contradicting the schema. Marginal gain over the schema remains modest since the enum and alias behavior are already documented structurally.

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 precisely what is returned: Cut Performance Index scores (overall, brilliance, fire, scintillation, tilt, symmetry, spread, shape-norm, leakage) for every cut sold, ray traced per gemstone. That is far more specific than a name restatement. It does not explicitly distinguish itself from siblings like get_cut or compare_cuts, so an agent must infer that this is the bulk-score feed rather than a single-cut lookup or a ranking tool.

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?

Gives clear operating guidance: 'Filter by cut, category or material; with no filter, every row,' which tells the agent both the filtering modes and the default sweep behavior. It also sets a hard usage constraint — 'Never compare or rank scores across materials' — which effectively routes ranking intent elsewhere. It stops short of naming the alternative tool for comparison or for single-cut details, leaving that inference to the agent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.