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

With no annotations, the description carries the full behavioral burden. It usefully discloses two behavioral facts: the result assumes a round brilliant cut, and density is corrected per stone (with a concrete ~9% error magnitude for diamonds vs moissanite). However, it says nothing about valid carat ranges, rounding, what happens with an unknown stone, or the return shape.

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 short sentences, front-loaded with the output ('Diameter in millimetres') before the assumptions. No filler. The density sentence is densely packed but each clause earns its place.

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 two-parameter, no-output-schema utility, the description covers the key domain trap (density varies by stone) and the cut assumption, but leaves out the default stone, expected numeric ranges, precision of the returned diameter, and any failure behavior — modest gaps for an otherwise simple converter.

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 coverage is 50%: 'carat' is self-documented ('Carat weight, e.g. 1.0') while 'stone' has only an enum and default. The description adds real semantic value by explaining why stone matters (density correction, ~9% diamond-vs-moissanite error), but it never states the moissanite default or what density table the non-default stones use, so it only partially compensates.

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 concrete verb-equivalent resource: 'Diameter in millimetres for a given carat weight', which tells the agent exactly what is produced. The qualifier 'Round brilliant cut' narrows the domain. It does not explicitly distinguish itself from the sibling mm_to_carat, so an agent must infer the direction from the name.

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?

Usage is only implied: the conversion direction and the 'density-corrected per stone' note suggest it should be called whenever carat → physical size is needed for a specific material. There is no explicit when-to-use statement, no when-not, and no named alternative such as mm_to_carat for the inverse case.

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