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

readOnlyHint=true already covers the safety profile, so the description's added value is the quota note ("Gratuito (uso limitado)") and the hard validation rule that dv_limite_pct is required for G4, both of which are behavioral facts not in the annotations. It stops short of describing what the response contains (dip magnitude vs. class limit comparison).

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?

Dense but economical: the method/source is front-loaded, then branch conditions, then parameter notes, then the quota line — no filler sentences. Some entries are terse to the point of opacity ("`XR` = X/R da X'd (ângulo da queda)"), a small cost against its compactness.

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 15-parameter calculation tool with no output schema, the description should say what comes back (ΔV result, pass/fail against the class limit) and sketch the class-limit semantics it references. It names them but leaves both the return shape and the ISO class limits implicit, so an agent can call it but cannot fully predict the result.

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 carry parameter meaning, and it does explain the hard ones well: `modo` and which params each branch needs, `XR`, the `cabo_mm2`+`cabo_m` pairing, `dv_limite_pct`, and `motor_fp_rotor_bloqueado`. However, roughly half the 15 parameters (xd_pct, degrau_kVA units, motor_Ip_In, tensao_V/Sn_kVA base, api_key) remain undocumented in both schema and description.

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 precise verb+resource: computes the transient voltage dip from a load step on a genset per ISO 8528-5 (voltage step), via X'd. The technical scope is unambiguous, but it never names or contrasts with the nearest sibling (partida_motor / tempo_partida_motor), which also deals with motor starting and could be confused with the `modo=motor` branch here.

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 does clarify the internal branch selection: `modo` ∈ {bloco (degrau_kVA+degrau_fp), motor (motor_kW, DOL)}, and flags `dv_limite_pct` as mandatory for classe_iso="G4". That is useful conditional guidance, but nothing says when to pick this tool over the sibling motor-starting tools — the choice is only implied.

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