femm_estimate

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

With no annotations, the description carries the burden and does reasonably well: it declares the calling convention (no name lists formulas), the unit system, and the idealisation-error caveat. It stops short of describing validation/error behavior for unknown formula names, but for a pure read-only computation this is adequate.

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 units and the no-name behavior, followed by concrete examples, with no filler sentences. It is dense but each clause adds either a formula name, an argument key, or a usage caveat.

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 parameterised estimator with no output schema and 0% schema description coverage, the description supplies the formula inventory, argument examples, and the self-documenting no-name mode. The main residual gap is that per-formula argument semantics must be discovered by an extra call, but the tool provides that path explicitly.

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 0%, so the description must compensate, and it does: three fully worked call examples show the exact shape of the args object and its keys (turns, current, gap, mu_r, pole_pairs, psi_d, etc.), and the formula list enumerates valid name values. It does not document every argument of every formula, but it points to the no-name listing mode for the full set.

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 states a specific verb and resource: evaluate analytic reference formulas in SI units to sanity-check FEMM results. The concrete examples (ccore_gap_b, dq_torque, skin_depth) and the formula list make the tool's function unmistakable and distinguish it from solver/measurement siblings like femm_solve and femm_point_values.

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?

It explicitly frames the use case ('Compare FEMM results to these within the idealisation error') and explains the no-name listing mode, giving clear when-to-use context. It does not name alternative siblings to prefer for other tasks, but for this standalone estimator the guidance is solid.

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