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

Annotations already establish that this is a safe, read-only, idempotent, closed-world lookup, so the bar is lower. The description adds real behavioral value beyond that: it returns a ranked list, it flags which readings fit and which do not, and it handles the over-the-limit refractometer case.

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

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

Three sentences, front-loaded with the action, then the input menu, then the critical scope caveat. No filler and no repetition of the title or annotations.

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

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

For a 7-parameter, all-optional, no-output-schema tool, the description covers the input space and describes the shape of the result (ranked stones with fitting/non-fitting readings). A small gap remains: it does not say what happens if no readings are supplied at all, given zero required parameters.

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

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

Schema description coverage is 100%, with enum values and examples already documented per parameter, so the schema does the heavy lifting. The description enumerates the same reading types but adds no syntax, ranges, or combination guidance beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (match/rank) and resource (test readings against seven gemstones), and the sibling context makes the distinction clear: gem_properties looks up data, compare_gemstones compares known stones, this one identifies from raw readings. The scope bound ('seven gemstones Digital Gemology covers') is explicit.

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

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

The 'Give any of:' list tells the agent exactly what kinds of input are accepted and that partial data is fine, and the closing caveat ('a lead among seven stones only, not an identification') sets the correct expectation for interpreting results. It doesn't explicitly name when to prefer a sibling tool, so it falls short of a 5.

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