femm_units_convert

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the valid conversion names, the aliases accepted for length units, the input/output model ('value in, result out'), and a concrete default (mu_r defaults to 1.05 for hc_from_br). It stops short of describing behavior on invalid conversion names or the exact return type.

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?

Front-loaded with the purpose followed by a dense but efficient enumeration of conversions and their requirements. The list is long, but each entry (with its arrow notation and dependency notes) carries distinct information, so little is wasted.

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 5-parameter pure-function tool with no output schema and no annotations, the description covers inputs, valid conversions, dependencies, and defaults well enough to invoke correctly. The main residual gap is the exact shape/type of the returned result, only hinted at by 'value in, result out'.

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 0%, so the description must compensate, and it largely does: conversion is enumerated with valid values, from_unit/to_unit are constrained to a unit set with aliases, mu_r's role and default are explained, and value is described via the input/output convention. Given zero schema-level documentation this is meaningful coverage, though the full set of conversion options is only partially mapped to their required parameters.

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?

The description opens with a specific verb+resource ('Unit conversions used with FEMM') and enumerates the conversion families it supports, so an agent immediately knows this is a standalone conversion utility. It is naturally unique among siblings (no other tool does unit conversion), so sibling differentiation is implicit rather than stated.

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 implied (convert values before feeding them into FEMM calls like mi_addmaterial, material definitions, etc.) and it gives the dependency that conversion='length' requires from_unit/to_unit. However, it never states when to prefer this over alternatives such as computing inline via femm_eval, and there are no explicit when-not conditions.

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