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

Annotations already establish it as a safe, idempotent, non-destructive read, so the bar is lower. The description still adds real behavioral context beyond the annotations: mg/mcg conversion is exact, IU conversion is conditional on profile data, and the failure mode is a named issue (iu_factor_missing) instead of a silent assumed factor. It also disclaims any dosing interpretation.

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 dense sentences with no filler. The core operation, the conditional caveat, and the scope disclaimer are each stated once and in priority order.

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?

With an output schema present and full schema coverage, the description only needs to carry edge-case and scope context, which it does: the IU precondition, the resulting error name, and the non-dosing disclaimer. Minor omission is that it never states which direction pairs are valid (mg↔mcg vs IU↔mass), leaving that to the enums.

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%, including the note that `peptide` is only needed for IU, so the baseline is 3. The description reinforces the peptide parameter's role and its failure mode but adds no format or syntax detail beyond the schema (e.g., the "2,5" input notation comes from the schema).

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 and resource (convert an amount between mg and mcg) and immediately scopes the harder case (IU ↔ mass requires a documented IU-per-mg factor). It is clearly distinguishable from sibling tools like solution_concentration or blend_concentrations, which deal with mixtures rather than unit arithmetic.

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 an explicit conditional rule: IU conversion only works when a peptide profile documents an IU-per-mg factor, otherwise you get an iu_factor_missing issue rather than an assumed factor. It also pre-empts misuse by stating this is arithmetic, not a dosing recommendation. It does not explicitly route between this and sibling tools, which keeps it 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.