Arc Flash Platform — Estudos Elétricos

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

The description adds behavioral context beyond the readOnlyHint annotation, detailing how parameters like xr_rede/xr_trafo affect peak current and asymmetry, and how grounding parameters govern phase-to-earth fault current. It also discloses that the tool is free with limited usage, which is additional transparency.

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 description is a single paragraph that front-loads the main purpose and then concisely explains key parameters and behaviors. While packed with information, it could be more structured (e.g., bullet points) for easier scanning, but it remains efficient and free of fluff.

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?

Given 17 parameters and no output schema, the description covers critical aspects but omits some details (e.g., default values for trafo_kVA, api_key purpose). However, it provides enough context for a knowledgeable user to invoke the tool correctly; some gaps remain for complete self-containment.

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?

Since schema_description_coverage is 0%, the description carries the full burden of parameter meaning. It explains relationships (e.g., potencia_curto_mva vs. icc_rede_kA, xr_rede/xr_trafo impact, grounding effects, cable parameters) that are not evident from the input schema alone, providing essential semantics for correct usage.

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 clearly states it calculates short-circuit (IEC 60909) and specifies the types: Icc 3φ/2φ/fase-terra, X/R, and peak. It also indicates the input methods and conditional behavior with transformer and cable, making it distinct from sibling tools which handle other electrical calculations.

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 description provides clear context on when to use the tool by explaining alternative input methods (potencia_curto_mva or icc_rede_kA) and conditional behaviors (com_transformador, com_cabo). It does not explicitly mention when not to use alternatives, but the tool's uniqueness among siblings reduces ambiguity.

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

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

Annotations only provide readOnlyHint=true. The description adds significant behavioral context: validated calculation, dual-current approach with worst-case governing, enclosure size correction, and usage limits. No contradictions with annotations.

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 description is dense but efficient: front-loads main outputs, adds details on standards, config, dual currents, and enclosure. Every sentence contributes, though a more structured format (e.g., bullet points) could improve readability. No wasted words.

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?

With 11 parameters and no output schema, the description covers main inputs and outputs (Ei, LAS, PPE) but leaves several parameters undescribed and does not explain return values or units. It is adequate for an expert user but incomplete for a novice.

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%. The description explains key parameters (config, t_arc_s, t_arc_reduzido_s, larg_mm/alt_mm/prof_mm) but does not cover several others (tensao_kv, ibf_ka, gap_mm, dist_trabalho_mm, api_key). It adds value beyond the schema but is incomplete.

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 clearly states the tool calculates incident energy, arc flash boundary, and PPE category, citing specific standards (IEEE 1584:2018, ABNT NBR 17227:2025). It distinguishes itself from sibling tools like 'calcular_curto_circuito' by focusing on arc flash, making the purpose unambiguous.

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 description provides context on when to use the tool (arc flash calculations per IEEE 1584/NBR 17227, voltage range 208V–15kV) and explains the two current levels, advising when to provide both clearing times. It does not explicitly list alternatives or exclusions, but the scope is clear.

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

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

Annotations provide readOnlyHint=true; description adds that it is free with limited use, a screening tool, and does not use IEEE 1584 motor. It also explains limitations like no gap/electrode configuration. No contradictions with annotations.

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 description is detailed and front-loaded with purpose, but is somewhat verbose. Given the complexity of the tool (three methods with different params), it is reasonably concise.

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?

The description covers methods and their parameter requirements well, but does not fully describe output format (e.g., for Lee/EPRI, no indication of return value units or type). Missing details on error conditions and units for common parameters.

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 has 0% description coverage; the description compensates well for the 'metodo' parameter and its dependencies, explaining each method's requirements. However, other parameters (tensao_kv, ibf_ka, t_ms) are not individually described, though their names are self-explanatory.

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 explicitly states the tool calculates incident energy for systems >15 kV using OSHA, Lee, or EPRI methods. It clearly distinguishes itself from IEEE 1584 and lower voltage tools, specifying scope and methodology.

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 description explains when to use this tool (systems >15 kV, screening not report) and provides detailed guidance for each method (OSHA, Lee, EPRI), including required parameters. However, it does not explicitly mention alternative sibling tools for lower voltage, though it is implied by the voltage threshold.

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

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

The description discloses key behavioral traits: it performs calculations, provides nominal current and standard when voltage is given, accounts for derating (Q∝V²), alerts for overcorrection at light load, and computes inrush current. These details add value beyond the readOnlyHint annotation, which is correctly assigned for a calculation tool.

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 description is a single paragraph that efficiently packs many details without redundancy. While it could benefit from bullet points or clearer separation of ideas, every sentence adds value, and it remains compact.

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?

Despite no output schema, the description explicitly mentions all key outputs (nominal current, standard, derating effect, overcorrection alert, inrush current). Given the complexity of 8 parameters, the description provides sufficient context for correct invocation.

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?

With 0% schema description coverage, the description fully compensates by explaining each optional parameter in detail: tensao_kV yields current and standard, Un_cap_kV affects derating, carga_min_pct triggers overcorrection alert, scc_MVA computes inrush current. Required parameters are implied by context.

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 clearly identifies the tool as sizing capacitor banks for power factor correction to a specific target (0.92) per ANEEL regulation. It also specifies additional outputs when voltage is provided, distinguishing it from sibling tools which cover other electrical calculations.

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 description states the primary use case (correct power factor to target) and explains the role of optional parameters, implicitly guiding when to include them. However, it does not explicitly mention when not to use the tool or list alternative tools, but the context makes the purpose clear.

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

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

The description adds behavioral context beyond the readOnlyHint annotation, detailing that the curve covers through-fault damage, includes ANSI and inrush points, and that the 'ligacao' parameter scales the curve for coordination on the other side. It also notes the tool is free with limited use, which is a behavioral disclosure.

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 description is a single paragraph that front-loads the purpose and standards, using backticks for parameters to separate information. It is relatively concise given the amount of detail, though it could be better structured with bullet points.

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?

The description explains the tool's purpose and some parameters, but lacks details on required parameters, return format, and units. Given the complexity (10 parameters, no output schema), it is adequate but incomplete.

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?

With 0% schema description coverage, the description must compensate. It explains the meaning and allowed values for fases, frequencia_falta, tipo, t_inrush_ms, and ligacao (5 of 10 parameters). However, it does not explain the required parameters (Sn_kVA, Vn_kV, Vcc_pct) nor api_key and k_inrush, leaving gaps.

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 clearly states the tool generates a transformer through-fault damage curve per IEEE C57.109/C57.12.59, listing specific outputs (category, maximum current, ANSI point, inrush point) and its purpose for coordinating upstream protection. It is distinct from sibling tools, which focus on other calculations.

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 description mentions the tool is used 'para coordenar a proteção a montante' (to coordinate upstream protection), implying its usage context. However, it does not explicitly state when to use it versus alternatives or provide when-not-to-use guidance.

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

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

Annotations declare readOnlyHint=true, and the description is consistent, stating it returns computed values without side effects. It adds behavioral context about the output calculations (voltage elevation, current, effective Q, tuning frequency, suggested voltage class) and optional resonance analysis. No contradictions.

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 description is concise: two sentences plus a final 'Gratuito.' It front-loads the purpose, then input instructions, then output list. Every sentence adds value without redundancy.

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?

The description is fairly complete given the tool's complexity (7 parameters, no output schema). It covers core functionality, input requirements, and output values, including an IEC standard reference. It misses constraints on input ranges and does not explain the api_key parameter, but overall provides sufficient context for an AI agent.

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?

Despite 0% schema description coverage, the description adds meaningful semantics for key parameters: p_pct (detuning factor XL/XC, e.g., 7 or 14) and L_mH (inductance). It specifies they are mutually exclusive, and that scc_MVA enables parallel resonance evaluation. It does not explain api_key or other optional parameters in detail, but provides significant value beyond the schema.

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 clearly states the tool computes detuned capacitor bank parameters (anti-resonance series reactor). It specifies inputs (p_pct or L_mH, Q_kvar, tensao_kV) and outputs (voltage across capacitor, reactor current, effective reactive power, tuning frequency, suggested voltage class). It distinguishes itself from sibling tools like power factor correction or short-circuit calculation.

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 description provides clear guidance on when to use: for designing a detuned capacitor bank. It explains that either p_pct or L_mH should be provided, and optionally scc_MVA for resonance evaluation. However, it does not explicitly state when NOT to use or mention alternatives among siblings.

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

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

The description adds context beyond annotations: it mentions the tool is free and follows a specific standard. Annotations already provide readOnlyHint=true, so the description complements by clarifying the calculation scope. It does not contradict annotations and adds value by stating the tool's cost-free nature.

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 description is a single paragraph that efficiently packs essential information. It front-loads the purpose and then lists key parameters with valid values. While it could be structured better (e.g., bullet points), it is concise without unnecessary repetition.

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?

Given the lack of output schema, the description does not explain what the tool returns, leaving a gap for the agent. It covers most parameters but omits some (fp, temp_ambiente_C). For a complex tool with 16 parameters, the description is adequate but incomplete without output specification.

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?

With 0% schema coverage, the description compensates by explaining many parameters (e.g., sistema options, metodo installation types, disjuntor default logic). It adds meaning not present in the schema, though a few parameters (fp, temp_ambiente_C) are not described. Overall, it significantly aids parameter understanding.

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 clearly states the tool's function: dimensioning low voltage cable cross-section per NBR 5410, covering ampacity, voltage drop, and overload coordination. It specifies the standard and key parameters, distinguishing it from siblings like calcular_curto_circuito or grupo_gerador which handle different tasks.

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 description details what the tool does but does not explicitly state when to use it versus alternatives. It implies usage for cable sizing per NBR 5410, but lacks contrast with sibling tools or conditions where this tool is inappropriate. This leaves the agent without explicit guidance on tool selection.

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

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

Annotations already declare readOnlyHint=true. The description adds value by explaining the calculation behavior, such as how xr affects saturation criteria and the thermal/dynamic checks. It does not contradict annotations.

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 description is dense but front-loaded with the primary purpose, then parameter details. Every sentence adds value. However, it could be more structured (e.g., bullet points) for easier parsing.

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?

Despite covering parameter meanings and logic, the description does not specify the output format (e.g., recommended CT model, calculated values). Given 15 parameters and no output schema, this is a notable gap. Also, api_key usage limits are vague ('uso limitado').

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?

With 0% schema description coverage, the description thoroughly explains almost all parameters (e.g., xr, I_load_A, Fter, Ith_A, Idyn_A, Rct_ohm, burden_VA, cable_ohm, relay_ohm, secundario_A, ALF, Icc_A, t_curto_s, tth_s). Only api_key is not explained, but it is optional. This compensation is excellent.

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 explicitly states that the tool dimensions a protection CT (IEC 61869-2) with specific criteria (smallest commercial primary not saturating under fault, considering burden and ALF). The verb 'dimensionar' and resource 'TC' are clearly identified, distinguishing it from sibling tools like calcular_curto_circuito.

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 description implies the tool is used for CT sizing but does not explicitly state when to use it versus alternatives (e.g., requiring prior fault current calculation) or when not to use it. No comparison with sibling tools is provided.

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

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

Annotations provide readOnlyHint=true. The description adds behavioral context: it is a calculation tool, free with limited use, and explains how exposure of faces affects cooling ('coberta = encostada na parede / em fila → aquece mais'). It does not contradict annotations and provides useful behavioral information beyond the structured fields.

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 description is a single dense paragraph that front-loads the main purpose. It efficiently conveys multiple parameter details without excessive length, though it could benefit from better structure (e.g., listing parameters). It is concise enough but not overly so.

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?

Given the complexity (15 parameters, no output schema), the description does not fully cover what the tool returns. It fails to describe the output (e.g., temperature rise value, pass/fail criteria). Also, several parameters (ventilado, n_particoes, area_ventilacao_cm2, etc.) are left unexplained, leaving gaps for the agent.

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. It explains key parameters: perda_W as power loss, dimensions in meters, face exposure options (exposto/coberto), tipo_instalacao (1-5), regime (BT/MT), and limite_equip_C. However, some parameters like n_particoes, ventilado, area_ventilacao_cm2, temp_ambiente_C, and api_key are not described, missing some semantics.

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 clearly states the tool calculates temperature rise in a low voltage panel per IEC 60890 and checks acceptance per 61439-1. The verb 'Elevação' and resource 'temperatura em painel' are specific, and it is clearly distinguished from siblings which address other electrical calculations.

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 description does not provide explicit guidance on when to use this tool versus alternatives. It implies usage for panel temperature rise calculation but lacks context such as prerequisites, limitations, or scenarios where other tools would be more appropriate. No when-not-to-use or alternative tool references are given.

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

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

Annotations include readOnlyHint=true, but the description says the document is 'preparado na sua conta da plataforma', implying creation or modification. This contradicts the readOnlyHint. The description adds workflow context but does not resolve the inconsistency.

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 description is two sentences, front-loading the key purpose. It is concise and avoids unnecessary details, though it could briefly mention parameters.

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?

The tool lacks an output schema and has no parameter documentation. The description does not explain what 'referencia_calculo' is or how the document generation process works, leaving a significant knowledge gap for the agent given the tool's complexity and sibling context.

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%, and the description does not explain any parameters. The required parameter 'referencia_calculo' and optional 'api_key' lack any semantic meaning or usage guidance in the description, leaving the agent without necessary context to fill them correctly.

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 title 'Memorial de cálculo (laudo na plataforma)' and description clearly state that the tool generates a signable calculation memorial document with ANSI/NBR label. It is distinct from sibling calculation tools which perform specific engineering calculations, not document generation.

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 description explicitly warns 'NUNCA é emitido autonomamente por IA', indicating the tool should not be used to autonomously issue the document. It clarifies that the document is prepared for review and signature by a technical responsible, providing clear when-to-use and when-not-to-use guidance.

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

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

Annotations already indicate read-only. Description adds behavioral context: free with limited usage, parameter overrides (dv_limite_pct), and mandatory conditions (G4 class). Does not contradict annotations.

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?

Description is compact and front-loaded with purpose, but the dense text could benefit from better structure (e.g., bullet points or separate lines for parameter groups). Every sentence contributes value.

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?

Given 15 parameters and no output schema, the description provides the calculation context and parameter meanings but does not specify the return value format or output fields. Some parameters (motor_Ip_In) lack explanation, and required parameters are not explicitly highlighted.

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?

With 0% schema coverage, the description explains many parameters (modo, XR, cable, dv_limite_pct, motor_fp_rotor_bloqueado) and their roles. However, it omits explanation of required parameters (tensao_V, Sn_kVA) and motor_Ip_In, leaving some semantics unclear.

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?

Description clearly states the tool computes transient voltage dip when applying a load step to a generator per ISO 8528-5. It specifies the method (via X'd) and distinguishes from sibling tools that handle other electrical calculations (short circuit, cable sizing, etc.).

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 description implies usage for generator load-step analysis but does not explicitly state when to use this tool versus alternatives (e.g., motor start or short circuit). No when-not-to-use or prerequisite conditions are provided.

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

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

The annotations already declare readOnlyHint=true, so the read-only nature is clear. The description adds that it is free and references IEEE C57.110 standards, but does not disclose other behaviors like authentication needs, rate limits, or error handling. With annotations covering safety, this is adequate but not rich.

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 description is two sentences with an example and standard references, no wasted words. It is front-loaded with the core purpose and includes a concrete input example, making it efficient and clear.

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?

No output schema exists, but the description enumerates the return values (K-factor, K-rating, F_HL, THD). For a simple calculation tool with one required parameter, this is nearly complete. However, it omits potential error conditions or invalid input handling, which prevents a perfect score.

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. It provides an example of the required 'espectro_harmonico' parameter format ('{"3": 70, ...}') and explains the output, but does not describe the optional 'api_key' parameter. This adds value beyond the raw schema but is incomplete for all 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 clearly states it computes the K-factor from a current spectrum and lists the specific outputs (K-factor, K-rating, F_HL, THD). The title reinforces the transformer context, distinguishing it from sibling tools like 'dano_transformador'.

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 description provides an example input format and mentions it is free, but it does not explicitly state when to use this tool versus alternatives among the many sibling tools. Usage context is implied by the tool name, but no direct guidance is given.

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

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

Annotations already declare readOnlyHint=true. Description adds that it is 'Gratuito (uso limitado)' and explains default filter scope. Does not detail return format or limits, but overall adds value beyond annotations.

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?

Three dense sentences covering purpose, default behavior, parameters, and limitation. No wasted words. Front-loaded with key purpose.

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?

Explains primary use case and parameter options. Lacks output format description (no output schema). Given it's a catalog listing, likely simple list; minor gap.

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 has 0% coverage. Description explains 'tipo' with allowed values and 'todos' to include all types. Does not explain 'api_key' but mentions free limited use. Compensates for schema gap significantly for two of three 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?

Description clearly states it lists the device catalog (devices_db) to discover device_id for use in tempo_de_atuacao. Specifies default filter (MCCB/ACB) and parameter effects. Distinct from all sibling tools, which are calculation tools.

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?

Explicitly states usage context: 'para descobrir o device_id usado no modo catálogo de tempo_de_atuacao.' Describes default behavior and parameter options. Does not explicitly list alternatives or when not to use, but context is sufficient.

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

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

Annotations already indicate readOnlyHint=true, so no destructive behavior. The description adds that it 'lists the shelf of calculations and tiers,' providing context beyond the annotation by specifying the nature of the listing.

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?

A single sentence with no unnecessary words. It is direct and front-loaded with the main action ('Lista a prateleira'). Every word earns its place.

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?

Given the tool has no parameters and only performs a simple listing, the description fully conveys what it does. No output schema is needed as the return is implied to be a list of calculations and tiers.

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?

No parameters exist, so the description does not need to add parameter semantics. Baseline 4 is appropriate as the description is complete regarding input.

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 clearly states 'Lists the shelf of electrical engineering calculations and the tier of each one.' It uses a specific verb (lista) and resource (prateleira de cálculos), and distinguishes this from sibling tools that are individual calculations.

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 description implies this tool is for browsing available calculations and their tiers. It does not explicitly state when to use it vs alternatives, but given no parameters and a listing purpose, the use case is clear. A more explicit 'use this to see all available tools' would improve it.

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

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

As anotações já indicam readOnlyHint=true, então a ferramenta é de leitura. A descrição adiciona que é gratuita com uso limitado, e detalha o modelo de cálculo, mas não revela comportamentos adicionais além do esperado para uma análise.

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?

A descrição é concisa e bem estruturada, listando parâmetros principais com formato claro. Não há redundâncias, mas poderia ser organizada em seções para melhor legibilidade.

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?

A ferramenta tem 21 parâmetros, sem esquema de saída, e a descrição não informa o formato do resultado (ex.: queda de tensão percentual). Informações sobre retorno e a maioria dos parâmetros estão ausentes, tornando-a insuficiente para uso autônomo do agente.

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?

Com 0% de cobertura no esquema, a descrição deveria explicar todos os parâmetros, mas só cobre fonte_tipo, metodo, fp_partida, Cp_Cn e C_load_pu (5 de 21). Muitos parâmetros importantes (como tensao_V, potencia_kW, cabos) permanecem sem explicação.

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?

O título e a descrição deixam claro que a ferramenta calcula o afundamento de tensão na partida de motor, usando modelo de divisor fasorial. Distingue-se dos irmãos por focar em afundamento, não em tempo de partida ou curto-circuito.

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?

A descrição não oferece orientações explícitas sobre quando usar esta ferramenta versus outras (ex.: tempo_partida_motor). Menciona que trafo dedicado e GMG são casos severos, mas não fornece critérios de escolha ou contraindicações.

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

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

Beyond the readOnlyHint annotation, the description discloses that SWBP returns zero without bends, details attachment and convention options, and mentions limited free usage. This adds valuable behavioral context.

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 description is reasonably concise and structured, using backticks for parameter names and listing constraints. However, it could be slightly shorter without losing clarity.

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?

Given the tool's complexity (16 parameters, no output schema, multiple standards), the description is incomplete. It fails to explain many parameters, including all six required ones, and does not describe return values.

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?

With 0% schema description coverage, the description must explain parameters. It covers only 7 out of 16 parameters (e.g., n_cabos, curvas_graus, attachment) and omits required ones like secao_mm2, material, and comprimento_m. This is a significant gap.

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 clearly states the tool computes cable pulling traction per IEEE 1185/525, including capstan traction, SWBP, duct occupancy, and max traction. It uses a specific verb ('tração de puxamento') and resource ('cabo'), and is distinct from sibling tools like short-circuit or power factor calculations.

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 description implies use for cable pulling design but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria. Usage is implied by the standards and parameters mentioned.

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

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

Annotations declare readOnlyHint=true, so the tool is read-only. The description adds that it is free with limited use, and clarifies the optional parameters' impact on which curves operate, going beyond the annotations.

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 description is moderately long but well-structured: first paragraph explains purpose and chaining, second paragraph details parameters. It is front-loaded with key information, though slightly dense.

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?

Given the tool's complexity (10 parameters, 1 required) and no output schema, the description is highly complete: it explains parameter roles, chaining, manual vs catalog modes, and even notes that the output tempo_s feeds into calcular_energia_incidente.

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?

Despite 0% schema description coverage, the description thoroughly explains each parameter's meaning (e.g., pickup_A, curva, tms, optional 50 parameters) and provides usage guidance (manual vs catalog mode), fully compensating for the missing schema descriptions.

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 clearly states it calculates protection device operating time using IEC/IEEE curves and explicitly distinguishes itself as the link between short-circuit and incident energy calculations, differentiating from siblings like calcular_curto_circuito and calcular_energia_incidente.

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 description explains when to use this tool (as part of a chain from short-circuit to incident energy) and how optional parameters modify behavior (only inverse operates if optional 50 parameters are omitted). It does not explicitly state when not to use, but the context is clear.

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

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

Annotations already declare readOnlyHint=true, indicating no side effects. The description adds behavioral details: use of RK4 method, calculation of thermal rotor blocked criterion, and reference to Petrobras N-313. This goes beyond the annotation by providing simulation methodology and context.

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 description is a single paragraph that efficiently conveys the tool's purpose, method, and key parameters without excessive verbosity. Front-loaded with the core simulation action. Minor improvement could be structuring with bullets.

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?

Given 17 parameters, no output schema, and simple annotations, the description explains the simulation scope and outputs (acceleration time, start/stall decision, thermal result) but lacks details on output structure and full parameter definitions. Adequate but could be more comprehensive.

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. It explains a subset of parameters (polos, inercia_kgm2, tipo_carga, conjugado_partida_carga_pu, conjugado_pleno_pu, t_rotor_bloqueado_s) but leaves others (e.g., potencia_kW, tensao_V, scc_MVA) unaddressed. Partial but not comprehensive.

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 clearly states that the tool simulates a direct start using RK4, calculates acceleration time, whether the motor starts or stalls, and rotor blocked thermal per Petrobras N-313. This specific verb+resource combination distinguishes it from siblings like partida_motor, which may have a different scope.

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 description implies usage for direct start simulation ('Simula a partida DIRETA'), but does not explicitly provide when-to-use/not-to-use guidance or mention alternatives among siblings. Adequate for implied context but lacks explicit exclusions.

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

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

Beyond the readOnlyHint annotation, the description details behaviors: formulas for TN and TT systems, conditions for situacao, effect of missing R_montante_ohm, and defaults for secao_pe_mm2. It also notes the tool is free with limited use. No contradictions with annotations.

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 description is a single dense paragraph that front-loads the main purpose and standard. While efficient, it could be structured into separate sentences or bullet points for clarity. Every sentence adds value, but some technical details (formulas) might be better placed in param docs.

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?

Given 17 parameters and no output schema, the description covers the input logic well but fails to describe the return value (e.g., what 'veredito' looks like). It mentions optimistic verdict but not the structure of results, leaving the agent guessing about the output format.

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?

Despite 0% schema coverage, the description explains many critical parameters: Ia_A, disjuntor_In_A + curva_mcb, i_dn_mA + RA_ohm, situacao, R_montante_ohm, X_montante_ohm, circuito_tipo, secao_pe_mm2. However, it omits explanations for T_op, api_key, sistema, material, comprimento_m, and secao_fase_mm2, relying on defaults to be self-explanatory.

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 clearly states the tool's purpose: verifying automatic disconnection protection per ABNT NBR 5410:2004 §5.1.2.2. It uses a specific verb ('Verifica') and resource ('proteção contra choque por seccionamento automático'), and distinguishes itself from sibling tools like calcular_curto_circuito by focusing on this specific standard.

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 description provides context on how to use parameters (e.g., TN vs TT systems, importance of upstream impedance), but does not explicitly state when to use this tool versus alternatives. It lacks differentiation from sibling tools, leaving the agent to infer usage without guidance on exclusions.

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