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

Annotations already declare readOnly, idempotent, non-destructive, closed-world semantics, so the safety profile is covered. The description adds a genuine domain invariant beyond the annotations — the Gy/Sv separation — which prevents a class of incorrect calls. It does not cover edge behavior on unknown units or case sensitivity, keeping it from 5.

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?

Two short sentences, zero filler, with the core operation stated first and the guardrail immediately after. Nothing could be removed without losing information.

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?

The tool is simple (3 required scalars, no output schema), and the description covers the operation and its main constraint. However, with zero enums on `from` and `to`, an agent has no way to know the accepted unit vocabulary (e.g. mGy, rad, rem, mSv) or how invalid units are handled. That gap is the main shortfall for otherwise adequate coverage.

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 100%, so the baseline is 3. The description does add meaning to `from`/`to` by constraining which unit pairs are legal, which matters because neither parameter has an enum. Beyond that it offers no syntax, casing, or accepted-value guidance.

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?

Uses a specific verb ('Convert') and a precise resource ('a radiation value between units of the same quantity'), so the operation and its scope are unambiguous. It does not name or differentiate from siblings, but the sibling list is entirely unrelated tool domains, so differentiation adds little here.

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?

Gives a clear operating condition (same quantity) plus an explicit exclusion: Gy and Sv are never converted into each other, with the reason given (needs a radiation weighting factor). That is a real when-not rule. It stops short of naming a fallback tool for the cross-quantity case, which keeps it off a 5.

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