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

Annotations already declare readOnlyHint=true, and the description adds genuinely new behavioral context: it discloses the free/limited-usage quota ("Gratuito (uso limitado)") and warns that omitting R_montante_ohm/X_montante_ohm yields an OTIMISTA (unsafe) verdict. That safety-critical caveat is exactly the kind of disclosure annotations cannot carry. It does not describe the response shape beyond the word "veredito".

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?

Extremely dense but zero waste: purpose and standard clause first, then the TN/TT formulas, then the parameters that alter the verdict, then the quota note. Parenthetical input hints are embedded inline rather than bulked into separate sentences.

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 17-parameter engineering calculation with no output schema and no schema descriptions, the description covers the decision-critical inputs but omits several that feed the Zs computation (comprimento_m, secao_fase_mm2, material, T_op) and never states what the result contains beyond a pass/fail "veredito". Adequate to call correctly in the common case, incomplete at the edges.

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% across 17 parameters, so the description must compensate and largely does: it explains Ia_A vs disjuntor_In_A/curva_mcb, i_dn_mA, RA_ohm, situacao (1 = dry/50 V vs 2 = wet/25 V with stricter Tab. 25 time), circuito_tipo's two enum values, secao_pe_mm2 (None → Tab. 58 minimum), and the montante impedance pair. It leaves T_op, material, secao_fase_mm2, comprimento_m, sistema and api_key undefined, which for a Zs calculation are non-trivial omissions.

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 with the governing standard clause: verifies shock protection by automatic disconnection per ABNT NBR 5410:2004 §5.1.2.2. It even names the two calculation regimes (TN: Zs ≤ U0/Ia; TT: RA ≤ 50/IΔn), so an agent knows exactly what computation is being performed and can distinguish it from siblings like calcular_curto_circuito or tempo_de_atuacao.

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 explicit input routing: for TN supply either Ia_A OR disjuntor_In_A + curva_mcb, for TT supply i_dn_mA + RA_ohm. This tells the agent which parameter path to take per system type, which is the main invocation decision. It stops short of naming when to prefer this tool over a sibling or what preconditions must already hold.

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