Arc Flash Platform — Estudos Elétricos

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

Annotations declare readOnlyHint=true, and the description aligns by describing a read-only calculation. It adds behavioral details such as IEC 60909 compliance, parameter effects on results, and usage limits, going 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?

The single paragraph is dense with information, front-loading the purpose and then explaining parameters and conditions. It is efficient with no redundant 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?

Given the complexity (17 parameters, calculation tool), the description covers main scenarios and key parameters. However, it omits output details and leaves some parameters unexplained, requiring additional inference.

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%, but the description explains many key parameters (e.g., `potencia_curto_mva`, `icc_rede_kA`, `xr_rede`, `tipo_aterramento`, `com_cabo`). However, some parameters like `tensao_kv` and `api_key` lack explanation.

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 short-circuit currents (Icc 3φ, 2φ, phase-to-ground, X/R, peak) per IEC 60909. It distinguishes from sibling tools which address other electrical engineering 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 explicit guidance on specifying the network via `potencia_curto_mva` or `icc_rede_kA`, explains conditions for transformer and cable scenarios, and notes free but limited usage. It does not explicitly exclude cases or mention alternative tools, but the sibling set is diverse.

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 the two current plateau calculation approach, the need for both clearing times, and the box size correction. It also mentions the tool is validated and free (limited use). These details add value beyond the readOnlyHint annotation, which is consistent. However, no output schema is provided, so return format is not fully detailed.

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 front-loaded with the core purpose, then methodically explains the two current plateaus and box parameters. It is mostly concise, though the technical jargon may be dense. Each sentence provides unique information, so no significant waste.

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 high parameter count (11) and lack of output schema, the description is incomplete. It omits explanations for voltage, current, gap, and working distance parameters. No information about error handling, validation, or return structure beyond mentioning Ei, LAS, and category. The tool is complex, and the description does not fully equip an agent to use it correctly.

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 explain parameters. It explains config (enum values), t_arc_s, t_arc_reduzido_s, and box dimensions (larg_mm, alt_mm, prof_mm) with defaults and correction. However, it does not explain tensao_kv, ibf_ka, gap_mm, dist_trabalho_mm, or api_key, leaving gaps for an AI agent. The description adds meaning 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 (Ei, cal/cm²), arc flash boundary (LAS), and PPE category using IEEE 1584:2018 / ABNT NBR 17227:2025. The verb 'calcular' and specific resources distinguish it from sibling tools which cover different electrical calculations like short circuit or power factor correction.

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 explicitly state when to use this tool versus siblings. It explains parameter usage (e.g., two current plateaus, box dimensions) but lacks direct guidance on context or prerequisites. The free usage note suggests a limitation but does not help the agent choose this tool over alternatives.

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, consistent with the description calling it a screening tool. The description adds behavioral context: it is a triagem (screening) not a full report, and for OSHA it returns a PPE band rather than a single point. No contradiction 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 concise, using a bullet-like format within a paragraph. The first sentence establishes scope, and subsequent sentences detail methods. No fluff, but the dense layout could be slightly more readable (e.g., proper bullet points). Still efficient.

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 explaining methods and their parameter requirements, the description lacks information on output format for all methods (only OSHA's PPE band is described). It does not specify return units, error handling, or voltage constraints. With 8 parameters and no output schema, more detail would improve completeness.

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 explain parameters. It explains 'metodo', 'tipo_trabalho', 'dist_trabalho_mm', and 'comprimento_arco_m' with conditions and example values. However, 'tensao_kv', 'ibf_ka', 't_ms', and 'api_key' are not described, leaving gaps for these 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 the tool calculates incident energy for systems >15 kV using methods outside IEEE 1584:2018/NBR 17227, and explicitly differentiates from the sibling tool 'calcular_energia_incidente' by noting the platform's IEEE 1584 motor is not used. The title also specifies 'triagem' (screening), reinforcing its limited 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 provides explicit guidance for each method: OSHA for conservative PPE band, Lee for theoretical upper bound requiring distance, EPRI for high voltage requiring distance and arc length. It implies when not to use (e.g., for ≤15 kV) but does not state alternatives explicitly. Also mentions 'uso limitado' (limited use), giving context on constraints.

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 contradicts the annotation 'readOnlyHint: true' by describing a computational design tool that performs calculations and provides outputs. The rule states score 1 if description contradicts annotations, hence this low score.

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 but efficiently front-loaded with the main purpose. Each sentence adds meaningful detail about specific parameters. It uses backticks for parameter names, aiding readability, though it could be slightly more 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?

Given the tool's complexity (8 parameters, no output schema), the description provides context for some parameters and their effects but does not specify the return format or overall output structure. Missing information on prerequisites or required data.

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 compensates partially by explaining 4 of 8 parameters (tensao_kV, Un_cap_kV, carga_min_pct, scc_MVA) and their implications. However, it fails to explain potencia_kW, fp_atual, fp_meta, and api_key, leaving some ambiguity.

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 'dimensiona o banco de capacitores para corrigir o fator de potência', specifying the verb and resource. It references the specific standard (REN ANEEL nº 1.000) and target power factor (0.92), distinguishing it from siblings like 'dessintonia_capacitor' which deals with detuning.

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 when to use (for power factor correction) but does not explicitly state when not to use or compare with alternatives. No mention of prerequisites or exclusions, leaving the agent to infer usage context.

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, and the description adds context about it being free with limited usage. It explains how parameters like ligacao affect the curve scaling. However, details on the 'limited usage' are lacking, and the absence of output schema is not compensated fully.

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 dense paragraph that front-loads the purpose and quickly covers key parameters. It is efficient for an expert audience, though slightly more structure (e.g., listing outputs separately) could improve readability.

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, no output schema), the description mentions outputs but does not fully describe return format or behavior. The 'limited usage' warning is vague, and the api_key parameter is not addressed. Some gaps remain for a complete contextual understanding.

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 explains several parameters (fases, frequencia_falta, tipo, t_inrush_ms, ligacao) but omits descriptions for required parameters Sn_kVA, Vn_kV, Vcc_pct, which are left to domain knowledge. This partially compensates 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 transformer through-fault damage curves per IEEE C57.109/C57.12.59, listing specific outputs (category, maximum through-fault current, ANSI point, inrush point) and its purpose for coordinating upstream protection. This distinguishes it from sibling tools like k_factor_transformador or 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 explicitly states the tool is used to coordinate upstream protection, providing context on when to apply it. However, it does not explicitly exclude alternatives or mention conditions when not to use it, but the specificity of outputs and standards gives clear 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 declare readOnlyHint=true, so the description adds value by explaining the computations (e.g., 'tensão ELEVADA V/(1−p)') and return values. However, it does not address authentication (api_key), side effects, or rate limits, though the 'Gratuito' note is a minor addition.

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 three sentences, concise and front-loaded with purpose. It efficiently covers inputs, outputs, and an optional parameter 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?

With 7 parameters, no output schema, and zero schema descriptions, the description is incomplete. It omits explanations for most inputs and does not detail the return format (e.g., whether outputs are individual values or structured). An agent would need to infer too much.

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 p_pct and L_mH (one must be provided) but does not describe the other 5 parameters (Q_kvar, tensao_kV, scc_MVA, Un_cap_kV, api_key). Only scc_MVA is briefly mentioned in 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 states the tool is for a detuned capacitor bank (anti-resonance reactor) and lists specific outputs, distinguishing it from sibling tools like calcular_curto_circuito or corrigir_fator_potencia. It uses a specific verb (devolve) and resource (banco de capacitores dessintonizado) and provides examples.

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 detuned capacitor design but does not explicitly state when to use this tool versus alternatives. It mentions an optional parameter for resonance evaluation but lacks guidance on prerequisites or comparison to similar tools like corrigir_fator_potencia.

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; the description confirms it is a dimensioning (calculation) tool and adds behavioral details (e.g., free, multiple calculations performed). No contradiction. It would benefit from mentioning that it does not modify anything.

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 efficiently packs parameter details and tool behavior into a single dense paragraph. No repetition, but the structure could be improved with lists or sections for readability.

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 16 parameters and no output schema, the description covers the purpose and many parameters but lacks explanation of return values, interpretation of results, and explicit differentiation from siblings. It leaves gaps for an agent to infer.

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 many key parameters (sistema, metodo, material, etc.) but omits others (fp, queda_max_pct, temp_ambiente_C). The partial coverage is helpful but not complete.

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 dimensions a cable section per NBR 5410, listing specific calculations (ampacity, voltage drop, overload coordination). It distinguishes from sibling tools which cover different electrical scenarios like short circuit or transformer analysis.

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 parameter details and indicates defaults, but does not explicitly state when to use versus alternatives or what prerequisites are needed (e.g., knowing Icc at origin). However, the technical context strongly implies its use for cable sizing.

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 key behavioral traits: it considers asymmetric fault saturation via X/R, thermal/mechanical robustness via Ith/Idyn, and mentions usage limits ('Gratuito (uso limitado)'). This fully compensates for the minimal 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 dense but well-structured paragraph, front-loading the main purpose and then detailing parameters. It uses backticks for parameter names, aiding readability. Minor improvement could be breaking into sentences or 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?

Given 15 parameters, no output schema, and 0% schema coverage, the description covers the main logic and several parameters. However, it omits the output format/return value and does not explicitly define all parameters, leaving some gaps for a complex tool.

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 (xr, I_load_A, Fter, Ith_A, Idyn_A, Rct_ohm) with specific context. However, a few parameters (api_key, Icc_A, etc.) are not explicitly defined, though some are inferable from context. Overall, it adds substantial meaning.

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 sizes protection CTs per IEC 61869-2/NBR 6856, with specific logic for saturation, burden, and ALF. It distinguishes itself from sibling tools by detailing its unique criteria.

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 explicitly state when to use this tool versus its siblings (e.g., calcular_curto_circuito). It lacks guidance on prerequisites or exclusion scenarios, relying on implicit understanding of the tool's purpose.

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 behavioral context about parameter effects (e.g., face coverings increase temperature) and notes limited free usage. However, it does not disclose return format or side effects, and with no output schema, the output behavior remains unclear.

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 purpose and standard. It uses backticks for parameter names, making key terms stand out. No wasted sentences, though it could be slightly restructured for readability. It earns its place for the number of parameters covered.

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 covers the main purpose and key parameters but leaves gaps: it doesn't explain all parameters, output format, or provide examples. The '2º veredito' reference is ambiguous. The complexity demands more detail for full completeness.

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 carries full burden. It explains meanings for 9 of 15 parameters including perda_W, dimensions, face enums, tipo_instalacao, limite_equip_C, and regime. Some parameters like api_key, ventilado, n_particoes are not explained. Overall, it adds significant value beyond schema titles.

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 internal air temperature rise per IEC 60890 and checks acceptance per IEC 61439-1, specifying the exact standard and function. It lists relevant parameters and distinguishes itself from sibling tools like calcular_curto_circuito or dimensionar_cabo, which are different 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 explicitly state when to use this tool versus alternatives. It implies usage for panel temperature rise calculations, but no guidance on when not to use it or which sibling to choose instead. The unique domain (thermal calculation) provides implicit context.

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 explains the document is prepared for review and signature, and is never autonomous. Annotations already declare readOnlyHint=true, so the description confirms the read-only nature and adds workflow 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 sentence with a dash, which is concise and front-loaded with the purpose. However, it could break into two sentences for clarity. Overall, 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?

The tool has no output schema and the description does not indicate what the tool returns. The meaning of 'referencia_calculo' is ambiguous. Given the complexity (generating a document), more details on input and output are needed for complete understanding.

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 the parameters, especially 'referencia_calculo' which is required. Without clarification on what value to pass (e.g., a calculation ID), the agent may be unable to use the tool 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 description clearly states the tool generates a signable memorial with ANSI/NBR label, and the title reinforces it is a calculation memorial/report. This distinguishes it from sibling calculation 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?

Explicitly states 'NUNCA é emitido autonomamente por IA' (NEVER issued autonomously by AI), providing a strong when-not-to-use guideline. It clarifies the tool prepares a draft for human review, not a final output, making usage boundaries 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 significant behavioral context beyond the readOnlyHint annotation: it explains the physics (transient reactance X'd), parameter roles (cable adds to ΔV, dv_limite_pct overrides class limits and is mandatory for G4), and mode-specific inputs. It accurately reflects a read-only computation with no side effects, consistent with the annotation.

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 but economizes words well. It front-loads the main purpose and lists key parameters with their roles. Some redundancy (e.g., repeating ISO reference) and lack of structural elements (bullets, sections) prevent a perfect score, but it is efficient overall.

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 detailed parameter descriptions, the tool lacks an output schema, and the description does not specify the return value (e.g., voltage dip percentage, pass/fail status). It also does not clarify default behaviors for all parameters (e.g., what 'Gratuito (uso limitado)' means for usage limits). With 15 parameters, more completeness is needed.

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 must explain all parameters. It does explain many key parameters (XR, modo, cabo_mm2, cabo_m, dv_limite_pct, motor_fp_rotor_bloqueado, degrau_kVA, degrau_fp, classe_iso, motor_kW, motor_Ip_In) and their contexts. However, it omits required parameters tensao_V and Sn_kVA, and does not provide complete mappings for all 15 parameters, leaving some 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?

The description clearly states the tool's function: computing transient voltage dip for a generator set load step per ISO 8528-5. It specifies the resource (grupo gerador) and action (degrau de carga) with technical detail, and distinguishes it from siblings like calcular_curto_circuito or partida_motor, which cover different electrical phenomena.

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 and mentions two modes (bloco, motor), which suggests different use cases. However, it does not explicitly state when to use this tool over alternatives, nor does it provide any 'when not' guidance. The note 'Gratuito (uso limitado)' hints at access limits but is unclear.

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 that it returns computed values (K-factor, K-rating, F_HL, THD) and is free, which is consistent and provides additional context beyond the annotation.

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 very concise: two sentences that front-load the purpose and add an illustrative example. Every sentence adds value, and there is no extraneous text.

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 no output schema, the description lists the four return values. Input format is explained with an example. Missing details on error handling or units, but sufficient for a straightforward computation tool.

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 compensates well for the required 'espectro_harmonico' parameter by providing an example and format specification. The optional api_key parameter is not explained, but it is minor given its default null.

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 K-factor and related metrics from a harmonic spectrum, specifying the input format and outputs. It distinguishes itself from sibling tools by focusing on transformer K-factor per UL 1561.

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 harmonic spectrum analysis and K-factor calculation, but does not explicitly state when to use this tool versus alternatives or provide prerequisites. Sibling context makes the domain clear, but no direct 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 does not contradict this. The description adds value by noting the default filter (only MCCB/ACB), the effect of 'todos=True', and the limited free usage. It goes beyond annotations without introducing inconsistencies.

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, front-loading the purpose, then detailing filtering parameters. Every sentence adds value, with no redundancy. It is well-structured for an AI agent.

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 3 parameters and no output schema, the description explains the main use case and two parameters well. However, it lacks explanation for 'api_key' and does not describe the output format or fields, leaving some context incomplete for an 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?

With 0% schema description coverage, the description adds meaning for 'tipo' (listing possible values and default) and 'todos' (explaining its effect), but completely omits 'api_key'. This is a gap for a 3-parameter tool, resulting in moderate semantic help.

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 lists the device catalog to discover device_id for tempo_de_atuacao. It specifies the default behavior (only MCCB/ACB) and filtering options. While it distinguishes from the related sibling tempo_de_atuacao, it does not contrast with other sibling tools like listar_ferramentas.

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 when to use this tool (to get device_id for tempo_de_atuacao), but does not explicitly state when not to use it or provide alternatives. The mention of 'Gratuito (uso limitado)' gives some guidance on cost, but overall usage context is adequate but limited.

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, so the description adds little beyond that. It mentions listing 'a prateleira' and 'tier', but no additional behavioral traits (e.g., no side effects, no rate limits). With annotations covering safety, 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?

Single sentence, front-loaded with the verb 'Lista'. Every word is functional with no redundancy. Highly concise and well-structured.

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 complete enough for this simple tool: it explains the output (list of calculations and tiers). However, it lacks detail on the return format or what 'tier' means. Given no output schema, slightly more context would be beneficial, but still sufficient.

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 schema coverage is 100%. The description adds meaning by specifying what is listed (engineering calculations and tiers), going beyond the empty schema. Baseline 4 is justified for a zero-parameter tool.

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 lists a 'prateleira de cálculos de engenharia elétrica' (shelf of electrical engineering calculations) and their tiers. It is specific about the resource and action, but does not define what 'tier' means, which could cause slight ambiguity.

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?

No explicit guidance on when to use this tool versus alternatives. However, as a catalog tool, usage is implicitly obvious: when an agent needs to discover available tools. No exclusions or context 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 already mark readOnlyHint=true, and the description adds behavioral context by explaining that without C_load_pu, acceleration is not evaluated, and that dedicated transformer and GMG are severe cases. 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 concise and front-loaded with the main purpose. It uses structured formatting with backticks for parameters. Every sentence adds value, though some abbreviations may reduce clarity for non-Portuguese speakers.

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 21 parameters, no output schema, and moderate complexity, the description explains the model and important inputs but lacks information about return values and the meaning of required parameters like potencia_kW and tensao_V. Assumes domain expertise.

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 compensates by explaining key parameters like fonte_tipo, metodo, fp_partida, Cp_Cn, and C_load_pu. However, many parameters (e.g., potencia_kW, tensao_V) remain undocumented, so it is not fully compensatory.

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 voltage dip during motor starting ('Afundamento de tensão na partida de motor'), specifies the phasor divider model, and distinguishes from sibling tool 'tempo_partida_motor' which focuses on starting time. The verb+resource is specific and 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 source types and methods but does not explicitly state when to use this tool versus siblings like 'calcular_curto_circuito' or 'tempo_partida_motor'. No when-not-to-use guidance is given, relying on domain knowledge.

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 set readOnlyHint=true, confirming no destructive side effects. The description adds useful behavioral context: 'Gratuito (uso limitado)' indicates it is free with usage limits, and the mention of an optional api_key suggests potential paid tiers. No contradiction 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 packs considerable information efficiently. While not perfectly structured for scanning, every sentence adds value and there is no superfluous wording. Slightly crowded but 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?

Given the tool has 16 parameters, 6 required, and no output schema, the description covers the core computations (tension, SWBP, occupancy, max tension) and key constraints. However, it omits the return format, units, and error handling, and does not fully explain the relationship between parameters. Adequate but not 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 carries full burden. It explains semantics for ~6 of 16 parameters (n_cabos, curvas_graus, curva_raio_m, attachment, convencao, swbp_classe/cabo_classe) but leaves many critical ones (secao_mm2, material, od_mm, peso_kg_m, duto_D_mm, comprimento_m, mu, incl_graus, api_key) without explanation, forcing users to rely on parameter names alone.

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 tension, sidewall bearing pressure, duct occupancy, and maximum allowable tension per IEEE 1185/525 standards. It uses specific verbs ('tração', 'SWBP', 'ocupação') and resources, distinguishing it from siblings like 'dimensionar_cabo' which sizes cables rather than analyzes pulling mechanics.

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 inline constraints for parameters like n_cabos ∈ {1,3}, attachment types, conventions, and classes, and notes that SWBP is zero without curves. However, it does not explicitly state when to use this tool versus alternatives (e.g., dimensionar_cabo), leaving usage context implicit.

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. A descrição complementa informando que a ferramenta é gratuita com uso limitado e que calcula um valor de tempo, sem efeitos colaterais. Não há contradição com as anotações.

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 bem estruturada em parágrafos e seções (função principal, encadeamento, MANUAL, CATÁLOGO, gratuidade). O conteúdo é informativo sem ser excessivamente longo, embora possa ser ligeiramente condensado.

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?

Para uma ferramenta com 10 parâmetros e sem esquema de saída, a descrição fornece contexto suficiente: explica a finalidade de cada parâmetro, o encadeamento com outras ferramentas e que o tempo de saída (tempo_s) é usado como t_arc_s na ferramenta calcular_energia_incidente. Isso torna a ferramenta autossuficiente.

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 de descrição no esquema, a descrição compensa amplamente ao explicar a maioria dos 10 parâmetros (pickup_A, curva, tms, instantaneo_A, t_disjuntor_ms, curto_tempo_A, t_curto_tempo_ms, device_id, corrente_falta_A). Apenas o parâmetro api_key não é abordado.

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?

A descrição indica explicitamente que a ferramenta calcula o tempo de atuação de um dispositivo de proteção para corrente de falta, usando uma curva composta 4-segmentos (IEC/IEEE). Além disso, especifica o encadeamento com as ferramentas irmãs 'calcular_curto_circuito' e 'calcular_energia_incidente', diferenciando-se claramente delas.

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 fornece orientações de uso ao recomendar o encadeamento 'calcular_curto_circuito → tempo_de_atuacao → calcular_energia_incidente' e explica parâmetros nas seções MANUAL e CATÁLOGO. Embora não mencione explicitamente quando não usar a ferramenta ou alternativas, o contexto de uso é claro.

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; the description confirms it is a simulation (no side effects). It adds behavioral context (RK4 method, I²t thermal check) but does not disclose limitations, error handling, or resource usage. Meets baseline but adds moderate 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?

One dense paragraph front-loaded with purpose but mixing method, parameters, and standard reference. Could be split into behavior and parameter sections. Not overly long but lacks clear structure for quick scanning.

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 read-only annotations, the description fails to describe the output (acceleration time, start verdict, thermal result), required parameters, or defaults. Sibling 'partida_motor' suggests overlap but is not addressed. Incomplete for effective agent decision-making.

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 names 6 parameters in a list ('polos', 'inercia_kgm2', etc.) but only provides minimal semantics (e.g., 't_rotor_bloqueado_s liga o veredito térmico'). Most parameters (e.g., 'potencia_kW', 'tensao_V') are unexplained. Insufficient detail for a 17-parameter tool.

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 simulates a direct motor start over time using RK4, computes acceleration time, start success or stall, and rotor blocked thermal protection per Petrobras N-313. It specifies the methodology and criterion, making the purpose highly specific and distinct from siblings (e.g., 'partida_motor' likely covers other start types).

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?

No explicit guidance on when to use this tool vs. alternatives. The description mentions 'DIRETA' but does not contrast with sibling 'partida_motor' or state prerequisites. The agent receives no context for 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?

Adds context beyond readOnlyHint by explaining the effect of missing upstream impedance and noting 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 dense but efficient, front-loading the purpose. It uses bullet-like lists and parentheses to pack information. Could be slightly more structured but no wasted 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?

Covers core functionality well, including formulas and parameter logic. However, it lacks explanation of the output format (no output schema exists) and fails to describe some parameters (T_op, material, comprimento_m). Adequate but with notable gaps.

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 explains the meaning and usage of most critical parameters (e.g., Ia_A, i_dn_mA, RA_ohm, R_montante_ohm, etc.). Some parameters like T_op, material, comprimento_m are not covered, but the description compensates significantly.

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 verifies automatic disconnection protection per NBR 5410, with specific formulas for TN and TT systems. It distinguishes itself from siblings like calcular_curto_circuito by focusing on shock protection rather than fault currents or 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?

Provides clear guidance on when to use TN vs TT, which parameters to provide, and warns about upstream impedance leading to optimistic results if omitted. However, it does not explicitly state alternatives or when not to use this tool.

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