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

Annotations only declare readOnlyHint=true, and the description adds real context beyond that: the governing standards, the free-tier usage limitation ('Gratuito (uso limitado)'), and the multipliers applied when `ligacao` references the other winding. It does not say anything about the shape or units of the returned curve.

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?

The purpose and standard come first, then parameter notes, then the ligação factors and the cost note — a sensible front-loaded order with little filler. The ligação multiplier sentence is terse to the point of being cryptic, but it earns its space.

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 10-parameter engineering calculation with no output schema and minimal annotations, the definition covers the domain and several inputs but omits the units/meaning of the required nameplate values and any indication of what the curve returns. An agent could call it but would likely need a retry to get the required inputs right.

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 carry the load; it does well on the enum-like inputs (fases, frequencia_falta, tipo, ligacao with explicit ×0.58/×0.87/×1.0 factors) and t_inrush_ms. However, the three required parameters Sn_kVA, Vn_kV and Vcc_pct are never explained, and k_inrush and api_key are undocumented, leaving half the inputs to inference.

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 deliverable: the transformer through-fault damage curve per IEEE C57.109/C57.12.59, listing the points produced (ANSI point, inrush point, max through-fault current). An agent can distinguish it from k_factor_transformador or tempo_de_atuacao by the referenced standard and the damage-curve output. It stops short of naming which sibling it replaces for coordination studies.

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?

The phrase 'para coordenar a proteção a montante' implies the coordination-study context, and the `ligacao` explanation gives the reason to reference the other side. There is no explicit when-not guidance and no named alternative (e.g. versus k_factor_transformador or tempo_de_atuacao), so usage must still be inferred.

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