Skip to main content
Glama

Digital Gemology: gem identification and gemstone properties

Match gem test readings

identify_gem
Read-onlyIdempotent

Match a stone's test readings against the 36 gemstones in Digital Gemology's data and rank them, saying which reading fits and which does not. Give any of: refractive index, birefringence, specific gravity, optic character, pleochroism, a spectrum line, or that the refractometer read over the limit. A match is a lead, not an identification.

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": "identify_gem"
  }
}

Input Schema

NameRequiredDescriptionDefault
pleochroismNoWhat the dichroscope shows: none, weak, distinct or strong.
birefringenceNoThe difference between the two readings, for example 0.008; 0 for a singly refractive stone.
over_the_limitNoTrue if the refractometer showed no reading because the stone is above about 1.81.
optic_characterNoFrom the polariscope: singly refractive (stays dark) or doubly refractive (blinks light and dark).
refractive_indexNoA refractometer reading, for example 1.765.
specific_gravityNoSpecific gravity, for example 4.0.
spectrum_line_nmNoA line or band seen in a hand spectroscope, in nanometres, for example 694.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

The annotations already declare readOnly, idempotent, non-destructive, closed-world, which fits a lookup tool. Beyond that, the description adds real context: the reference set is bounded to 36 stones in a named data source, partial inputs are accepted, and the result is probabilistic ('a lead, not an identification'). That last point is the kind of interpretation caveat an agent cannot get from annotations. It does not describe ranking order or how many candidates come back.

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 core action before the input list, and the final caveat is the right thing to end on. The middle clause is a long one but each element is functional. No filler sentences.

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 does the work of indicating that results are ranked candidates with per-reading fit. Combined with annotations covering safety and the fully described schema, an agent has enough to call it correctly. The only gap is the rank output's form (count of matches, confidence), which is not sketched.

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% and the enum parameters are well documented, so the schema carries the parameter burden. The description adds only the framing that any subset of the seven readings may be supplied. It adds no units, ranges, or precedence rules beyond what the schema already states.

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 specific verb and resource: 'Match a stone's test readings against the 36 gemstones... and rank them,' and even summarizes the output ('saying which reading fits and which does not'). That is far more than a restated title. It never names compare_gemstones or gem_properties, though, so an agent must infer the routing boundary itself.

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?

It gives usable input guidance -- 'Give any of:' followed by the accepted readings, implying a partial reading set is enough. The closing caveat 'A match is a lead, not an identification' also frames how to treat results. But there is no when-to-use versus when-not guidance and no mention of the sibling tools, so a caller cannot tell from this text how it differs from gem_properties.

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.