Skip to main content
Glama

Digital Gemology: gem identification and gemstone properties

Tell two gemstones apart

compare_gemstones
Read-onlyIdempotent

Two gemstones side by side, and the tests that tell them apart: refractive index, birefringence (doubling of back facets, polariscope), specific gravity, dispersion (fire), hardness, pleochroism and spectrum, each with the free tool that shows it. For questions like 'how do I tell diamond from moissanite?'.

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": {
      "gemstone_a": "<gemstone_a>",
      "gemstone_b": "<gemstone_b>"
    },
    "name": "compare_gemstones"
  }
}

Input Schema

NameRequiredDescriptionDefault
gemstone_aYesThe first gemstone, as its slug.
gemstone_bYesThe second gemstone, as its slug.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / gemstone_a / enum
      Previous value: -[
      -  "diamond",
      -  "moissanite",
      -  "cubic-zirconia",
      -  "ruby",
      -  "sapphire",
      -  "emerald",
      -  "amethyst"
      -]New value: +[
      +  "diamond",
      +  "moissanite",
      +  "cubic-zirconia",
      +  "ruby",
      +  "sapphire",
      +  "emerald",
      +  "amethyst",
      +  "aquamarine",
      +  "morganite",
      +  "tanzanite",
      +  "topaz",
      +  "tourmaline",
      +  "pyrope",
      +  "almandine",
      +  "spessartine",
      +  "grossular",
      +  "demantoid",
      +  "spinel",
      +  "peridot",
      +  "citrine",
      +  "quartz",
      +  "opal",
      +  "jadeite",
      +  "nephrite",
      +  "turquoise",
      +  "chrysoberyl",
      +  "alexandrite",
      +  "zircon",
      +  "kunzite",
      +  "iolite",
      +  "moonstone",
      +  "yag",
      +  "ggg",
      +  "strontium-titanate",
      +  "glass",
      +  "synthetic-rutile"
      +]
    • changedInput schema / properties / gemstone_b / enum
      Previous value: -[
      -  "diamond",
      -  "moissanite",
      -  "cubic-zirconia",
      -  "ruby",
      -  "sapphire",
      -  "emerald",
      -  "amethyst"
      -]New value: +[
      +  "diamond",
      +  "moissanite",
      +  "cubic-zirconia",
      +  "ruby",
      +  "sapphire",
      +  "emerald",
      +  "amethyst",
      +  "aquamarine",
      +  "morganite",
      +  "tanzanite",
      +  "topaz",
      +  "tourmaline",
      +  "pyrope",
      +  "almandine",
      +  "spessartine",
      +  "grossular",
      +  "demantoid",
      +  "spinel",
      +  "peridot",
      +  "citrine",
      +  "quartz",
      +  "opal",
      +  "jadeite",
      +  "nephrite",
      +  "turquoise",
      +  "chrysoberyl",
      +  "alexandrite",
      +  "zircon",
      +  "kunzite",
      +  "iolite",
      +  "moonstone",
      +  "yag",
      +  "ggg",
      +  "strontium-titanate",
      +  "glass",
      +  "synthetic-rutile"
      +]
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world enum set, so the safety profile is fully covered. The description adds useful content disclosure about what the output contains — the test list (birefringence, dispersion, pleochroism, spectrum, etc.) — which is real value beyond the annotations, but it says nothing about output structure or how the "tool that shows it" references are presented.

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?

Two sentences, front-loaded with the comparison purpose before the supporting test list, and nothing is padded. The trailing clause "each with the free tool that shows it" is slightly vague and the test inventory is long, but each item is informative rather than filler.

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?

For a two-enum-parameter, read-only comparison tool with no output schema, the description adequately conveys what an agent will get back (a per-test breakdown pointing to the tool that demonstrates each test). It is nearly complete; only the shape and ordering of the returned comparison data remain unstated.

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 100% with both parameters enumerated and documented as slugs, so the schema carries the semantic load. The description's mention of diamond vs. moissanite loosely maps to enum values but adds no format, case, or ordering guidance beyond the schema.

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 states a clear verb and resource: comparing two gemstones and listing the tests that distinguish them, with concrete examples (refractive index, birefringence, specific gravity). It implies but never explicitly names how it differs from siblings like gem_properties or identify_gem, so it stops short of full sibling differentiation.

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 trigger is made explicit with the example question "how do I tell diamond from moissanite?", which tells an agent exactly what kind of user request maps here. It gives no exclusions or alternative routing (e.g., use gem_properties for a single stone, identify_gem for an unknown specimen), so the agent must infer the boundaries.

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.