Delegum

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

The description adds behavioral context: it not only calculates but also compares options and recommends. Annotations indicate readOnlyHint=true, which is consistent. No contradictions. However, it does not discuss edge cases or error handling.

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?

Two sentences, concise, front-loaded with the purpose. Every word is necessary and no filler.

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 mentions the output includes interest savings and a recommendation, which is sufficient. It could briefly mention the output format, but overall it is complete enough for the complexity.

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 100%, so the schema already describes all parameters. The description adds a high-level explanation of what the tool does (compare options) but does not add specific parameter meaning beyond the schema. Baseline 3 is appropriate.

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 the effect of early amortization for a mortgage (French system), compares two options (reduce monthly payment or reduce term), and recommends the best option. It is a specific verb+resource and distinguishes from sibling financial calculators.

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 use case (early amortization of a mortgage) but lacks explicit when-to-use or when-not-to-use guidance or alternatives. It is clear enough for the context but could be improved with 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?

Annotations already provide readOnlyHint=true, which the description complements. The description discloses the calculation formulas (60%/75% for common, 75% for accidents) and return details (daily, monthly, total, loss). 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 concise (one sentence) but packs necessary information: calculation rules, return types, and contingencies. It is well-structured and clearly worded.

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 is a calculator with complete schema descriptions and annotations, the description covers the calculation logic and output values adequately. No output schema but return values are described. Contextually complete for the task.

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 100%, so the schema already describes parameters. The description does not add parameter-specific details beyond mentioning 'días de baja' implicitly. Baseline 3 is appropriate.

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 sick leave subsidy for employees, specifies two types (common contingency and occupational accident) with exact percentage formulas, and mentions the return values (daily, monthly, total, loss). This distinguishes it from sibling calculators like calcular_pension_publica or calcular_jubilacion_anticipada.

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 sick leave calculations but does not explicitly discuss when to use this tool versus other calculators in the sibling list. No guidance on prerequisites, limitations, or when not to use 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?

Annotations already declare readOnlyHint=true, so the tool is safely read-only. The description adds value by specifying the computed outputs (gap, capital, monthly savings), which goes beyond the annotation. No contradictions present.

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 that efficiently communicates the tool's purpose and outputs without unnecessary words. It is front-loaded with the core action.

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 the main outputs but does not detail the formulas, assumptions (e.g., using rentabilidad_anual for savings growth), or result units. Given no output schema, slightly more detail would be beneficial, but it is largely complete.

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 100%, so parameters are fully documented. The description does not add any extra meaning to parameter semantics, matching the baseline score of 3.

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 the retirement gap, including the loss from salary to pension, required capital, and monthly savings. The verb 'calcula' and resource 'brecha de jubilación' are clearly defined, distinguishing it from siblings like 'calcular_jubilacion_anticipada' or 'calcular_pension_publica'.

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 no guidance on when to use this tool versus alternatives. Among siblings, there are other retirement-related tools, but no conditions, prerequisites, or exclusions are 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 already include readOnlyHint=true. The description adds context by explaining the calculation rule and outputs. No contradictions; the description enhances understanding without repeating 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 two sentences with clear front-loading of purpose, followed by output list and sibling tool references. No wasted words, and the structure is easy to parse.

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 no output schema, the description fully covers the return values: maximum capital, max price, available down payment, and financing percentage. It also explains the rule and gives sibling tool context, making it complete for a calculator 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 coverage is 100% with descriptions for all 6 parameters. The description restates default values and the effort threshold but does not add significant new meaning beyond the schema. Baseline 3 applies.

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 estimates the maximum mortgage using the Bank of Spain rule (esfuerzo ≤ 30-35%). It specifies the returned values and distinguishes from siblings like 'calcular_hipoteca' and 'consulta_compra_vivienda'.

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 advises when to use this tool vs alternatives: for monthly payment details use 'calcular_hipoteca', for a complete purchase with taxes use 'consulta_compra_vivienda'. This provides clear context for agent decision-making.

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 set readOnlyHint=true, which is consistent. The description adds transparency about the calculation behavior: fixed amount per child, maximum of 4 children, 14 pagas per year, and the legal context that the requirement for additional conditions for men is removed. 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 a single paragraph that efficiently conveys purpose, amount, conditions, and legal update. All sentences are informative. It could be slightly more structured (e.g., using bullet points for conditions), but it remains clear and focused.

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 thorough for parameters and logic, but it lacks an explicit description of what the tool returns (e.g., the complement amount, total pension with complement). Given there is no output schema, this omission is a gap. It implies the return but does not state it clearly.

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 100% with all 6 parameters described. The description adds significant value beyond the schema: it explains that 'sexo' is now only informative due to legal change, it details the meaning of 'num_hijos' (born alive or adopted), it clarifies that 'tipo_pension' only contributory types qualify, and it provides defaults for 'otro_progenitor' and 'fecha_hecho_causante'. This enriches 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 explicitly states the tool calculates the 'complemento de pensión para la reducción de la brecha de género' with legal reference (art. 60 LGSS) and explains the fixed amount per child (36,90 €/mes in 2026, max 4 children, 14 pagas). This clearly distinguishes it from sibling tools like 'calcular_pension_publica' or 'calcular_pension_viudedad' which are base pension calculations, not this specific supplement.

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 includes explicit requirements: contributory pension, hecho causante from 04/02/2021, at least one child, and that the other parent is not receiving it. It also notes the legal change (STJUE C-623/23 and STS 09-jul-2025) making it equal for both genders. While it does not explicitly compare to alternatives, the conditions are clearly stated, guiding appropriate use.

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, indicating no side effects. The description adds behavioral context by specifying the contribution system and inclusion of the flat rate, which is beyond what annotations provide. 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?

Single sentence, front-loaded with the action and resource, no extraneous words. 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?

Given the tool's simplicity (two parameters, calculation only), the description adequately covers purpose, system, and special case. No output schema needed as return is likely a simple number.

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 descriptions for both parameters are already clear (net monthly income and flat rate flag). The description reiterates the context without adding new semantic detail beyond what the schema provides. With 100% schema coverage, baseline 3 is appropriate.

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 the monthly Social Security contribution for self-employed workers under the real income system (RETA), including the flat rate for new self-employed. It distinguishes itself from sibling tools by specifying the exact contribution type and the specific regulation (2025/2026).

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 for calculating the monthly quote, but it does not explicitly state when to use it versus alternatives like 'consulta_autonomo' or 'calcular_gastos_deducibles_autonomo.' No when-not-to-use or alternative names 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?

Annotations already indicate readOnlyHint=true, so no contradiction. The description adds important behavioral context: it clarifies that the deduction reduces taxable base (not tax directly) and that it estimates savings using the marginal rate. It also specifies legal articles and amounts. This goes beyond typical calculation descriptions, though it does not detail all edge cases or assumptions.

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 of about 4 sentences, efficiently conveying purpose, legal basis, amounts, and behavior. It front-loads the main action. It could be slightly more structured (e.g., bullet points for amounts) but is concise and clear without 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?

Given the tool has no output schema and 4 parameters, the description lacks explicit mention of return values or expected output format. It states it 'calculates' and 'estimates savings' but does not specify whether it returns a single number, a breakdown, or an object. For a complete understanding, an agent might need to infer the output from context. Additionally, it does not address potential errors or prerequisites (e.g., tax year).

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 100% with each parameter having a description. The tool description adds meaning by explaining the amounts associated with the 'grado' parameter (e.g., 3,000€ for 33%-64%) and the additional 3,000€ for assistance needs, which enriches understanding of 'necesita_asistencia'. However, it does not explicitly describe the 'titular' or 'tipo_marginal' parameters 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 calculates the minimum for disability in IRPF, with specific legal references (Ley 35/2006, arts. 60-65) and amounts based on disability degree and assistance needs. It also explains it estimates tax savings using marginal tax rate and notes it reduces taxable base, not tax directly. This specificity distinguishes it from sibling tools like calcular_irpf or other deduction calculators.

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 when calculating the disability deduction in Spanish IRPF, but it does not explicitly state when to use this tool versus alternatives (e.g., other deduction calculators or general IRPF estimator). No explicit 'when not to use' or comparison with siblings is provided, leaving some ambiguity for an AI agent.

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 a calculation. The description adds behavioral details: it applies a limit based on social security contributions and subtracts advanced payments. 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 a single sentence that efficiently packs all key information: purpose, amounts, conditions, and limits. No redundant words, front-loaded with essential details.

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 the calculation logic, conditions, and parameter roles. However, it does not explicitly state the return value format (e.g., a number). Given no output schema, a slightly more explicit return type 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 coverage is 100% with good descriptions for each parameter. The description adds value by explaining how parameters relate to the calculation (e.g., cotizaciones as limit, gastos guardería as increment). This exceeds the baseline of 3.

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 specifies the verb 'Calcula' and the resource 'deducción por maternidad en el IRPF', along with concrete amounts (1.200€/año, 1.000€/año). It clearly distinguishes from sibling tools, which cover different tax deductions or 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 when to use this tool (for maternity deduction), provides context on limits (cotizaciones, abono anticipado), but does not explicitly state when not to use or offer alternatives. Among many similar siblings, the specificity 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 indicate readOnlyHint=true, which is consistent with a calculation tool. The description adds context about the type of calculation (tariffs, coefficients, bonuses) and the important integration warning. No contradictions. Slightly more detail on behavioral traits would be beneficial but not necessary given 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?

Two sentences with zero waste: the first explains the core calculation, the second provides a critical usage warning. Highly efficient and front-loaded with essential information.

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 of a tax calculation tool with 5 parameters and no output schema, the description adequately covers purpose and usage guidelines but does not describe the output format or result details. This is a gap for a tool where the user would want to know what they get back.

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 100%, so the baseline is 3. The description adds high-level context (state/Catalan tariffs, coefficients by wealth, bonuses) that hints at parameter roles but does not provide specific syntax or format beyond what the schema already offers. Marginal added value.

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 the Impuesto de Donaciones (ISD) in Spain, specifying it uses state or Catalan tariffs, coefficients by wealth, and regional bonuses for lifetime family donations. It distinguishes itself from the sibling tool 'comparar_donacion_vs_herencia' by providing a clear use-case distinction.

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 when to use (donations in life between family members) and when not to use (comparing donation vs inheritance), directing the user to the alternative tool 'comparar_donacion_vs_herencia'. This provides clear 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?

The description adds behavioral context beyond the readOnlyHint annotation by specifying the outputs (reserva de puesto, meses que computan a la SS, coste total). It does not contradict annotations and provides useful details about each leave type's characteristics.

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, well-structured paragraph that front-loads the main purpose and efficiently delivers all necessary information without redundancy. Every sentence adds 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?

Despite the absence of an output schema, the description adequately explains the return values (reserva de puesto, meses que computan a la SS, coste total) and covers the tool's scope. It is complete for a calculation tool with 5 parameters and no nested objects.

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 100%, but the description adds meaning by explaining that 'voluntaria' has restrictions (4 meses–5 años, sin reserva) and that 'cuidado de hijo' includes primer año con reserva. This goes beyond the schema's brief 'Tipo de excedencia' and 'Edad' 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 rights and costs of a labor leave (excedencia), listing specific types (voluntaria, forzosa, cuidado de hijo, cuidado de familiar) with their constraints. This distinguishes it from sibling tools like calcular_reduccion_jornada or calcular_prestacion_maternidad_paternidad.

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 by detailing the types of leaves and what the tool outputs, but does not explicitly mention when to use it versus alternatives or specify exclusions. The context is sufficient for an agent to infer usage, but lacks explicit 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 readOnlyHint=true, so the tool is non-destructive. The description adds context by listing specific components included and excluding indemnización, which is 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 two sentences, very concise, and front-loads the purpose. Every sentence is essential and there is no 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 tool has 5 parameters and no output schema, the description sufficiently covers what the tool calculates and excludes. It could mention that results are estimates or depend on jurisdiction, but overall it is complete enough.

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 100%, so all parameters are described. The description does not add additional parameter-level details beyond what the schema already provides, so a baseline score of 3 is appropriate.

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 'finiquito' (severance) covering unused vacation, proportional extra payments, and pending salaries. It explicitly distinguishes from the sibling tool 'calcular_indemnizacion_despido' by naming it and stating what is excluded.

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 when to use this tool (for finiquito calculation) and when not to (for indemnización por despido, directing to a specific sibling tool). This fully meets the criteria.

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?

Las anotaciones ya indican readOnlyHint=true, pero la descripción va más allá al especificar que aplica FIFO, que calcula la compensación de pérdidas con límites (25%) y que indica el monto pendiente de compensar. Esto proporciona contexto conductual valioso que no está en las anotaciones ni en el esquema.

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?

La descripción es breve, directa y está redactada en tres oraciones que cubren el propósito central (cálculo de ganancia/pérdida y tributación), el método (FIFO) y la información adicional (compensación de pérdidas). No contiene información irrelevante ni redundante.

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?

Aunque no hay esquema de salida, la descripción ofrece una idea clara de lo que devuelve: importe de ganancia/pérdida, compensación y pendiente. Es suficientemente completa para un agente, considerando la complejidad de una calculadora fiscal de criptomonedas.

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?

El esquema de entrada ya describe todos los parámetros con detalle (cobertura 100%). La descripción general no añade semántica adicional a los parámetros más allá de lo que ya está en el esquema. Se mantiene la línea base de 3 para este caso.

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?

El título y la descripción detallan de manera precisa y específica que la herramienta calcula la ganancia o pérdida patrimonial por operaciones con criptomonedas (venta, permuta, pago, donación) y su tributación en el IRPF, aplicando el criterio FIFO. Además, se distingue claramente de las herramientas hermanas, que son otras calculadoras/impositivas, por lo que un agente puede identificar sin ambigüedad su propósito.

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?

La descripción no proporciona instrucciones explícitas sobre cuándo usar esta herramienta en lugar de otras similares. Aunque por el contexto se infiere que debe usarse para operaciones con criptomonedas, no se mencionan alternativas ni se indican exclusiones. La puntuación se ajusta al estándar de 'uso implícito'.

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; description adds value by explaining no modification occurs and detailing tax rules (e.g., finca rústica exempt from IVA and plusvalía). No contradiction.

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?

Front-loaded with purpose and usage; second part details rules per type. Some redundancy could be trimmed, but overall 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?

No output schema, and description does not explain what the tool returns (e.g., breakdown of taxes, total cost). For a calculation tool, this is a notable 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 coverage is 100% (baseline 3). Description adds meaning by explaining when parameters apply (e.g., anejo_de_vivienda only for garaje/trastero, renuncia_exencion_iva for local/nave/rústica) and their tax implications.

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 verb 'calcula' and resource 'impuestos y gastos de comprar un inmueble que NO es una vivienda', listing specific types (garaje, local, etc.). It distinguishes from sibling by naming 'consulta_compra_vivienda' for houses.

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 says when to use ('cuando la pregunta sea...') and when not ('Para una vivienda usa consulta_compra_vivienda'). Provides usage rules per property type.

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 indicate readOnlyHint=true, which the description does not contradict. The description adds detailed behavioral context about special rules (30% for household supplies, 50% for mixed-use vehicle, 5% global provision) that go beyond schema 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 concise paragraph. It front-loads the core purpose, then efficiently enumerates key special rules with specific percentages. No extraneous words or 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 14 parameters and no output schema, the description covers the calculation logic well. It explains how inputs relate to deduction limits. However, it does not describe the output format (likely a single deduction amount).

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?

All 14 parameters have schema descriptions (100% coverage). The tool description adds interaction rules (e.g., pct_vivienda_afecta only used with vivienda_habitual, vehiculo_uso_exclusivo flag changes deductibility), enhancing understanding beyond individual parameter docs.

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 specifies the tool calculates deductible expenses for Spanish self-employed in direct estimation (normal or simplified). It lists specific rules (supplies, vehicle, insurance, amortization) and differentiates from siblings like calcular_cuota_autonomo or calcular_modelo_130.

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 annual deductible expense calculation in IRPF but does not explicitly state when to use this versus other similar tools (e.g., calcular_modelo_130 for quarterly). No when-not-to-use or alternative guidance 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 already declare readOnlyHint=true. The description adds behavioral context (calculates, not modifies) and details about supported mortgage types, enhancing transparency 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 description is two concise sentences, front-loaded with key outputs and supported types. Every sentence contributes 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 lists expected outputs (monthly payment, total interest, ratio) and supported mortgage types. Absence of output schema is partly compensated by listing outputs, but could mention return format or limitations.

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 descriptions cover 100% of parameters with detailed info. The description adds no new parameter-specific details beyond the schema, so baseline score of 3 is appropriate.

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 a Spanish mortgage (French system) and lists key outputs (monthly payment, total interest, payment-to-income ratio). It explicitly distinguishes from sibling 'consulta_compra_vivienda' for complete purchase queries.

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 to use 'consulta_compra_vivienda' for a complete purchase consultation, but does not elaborate on other exclusions or alternative tools beyond that.

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 goes well beyond the readOnlyHint annotation, detailing the specific tax rules applied (exemptions, thresholds, regional scales, pension plan exemption). It also indicates the result is an estimate ('orientativa'), providing full behavioral context for the calculation.

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 main purpose, key rules, and limitations. It is front-loaded with the core action and provides necessary details without 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 the complexity of Spanish wealth tax (multiple regional regimes, exemptions, thresholds) and the absence of an output schema, the description is remarkably complete. It covers the main components, exclusions, and when not to use the tool, providing sufficient context for correct usage.

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 100% with detailed parameter descriptions. The tool description adds overall context for the calculation (e.g., how exemptions apply) but does not add new meaning for individual parameters beyond what the schema provides. Baseline 3 is appropriate.

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 wealth tax for individuals, determining filing obligation and estimated tax using regional scales and exemptions. It specifies the scope (no business holdings, no foral territories), which distinguishes it from potential sibling tools for other tax calculations or business wealth.

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 for individuals without business shares or non-listed companies, and excludes foral territories (Navarre, Basque Country). It does not directly name alternative tools for excluded cases, but provides clear conditions for use.

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 provide readOnlyHint=true, so the tool is safe to call. The description adds transparency by stating it provides estimates and is indicative (non-binding), and clarifies limitations (no CCAA or foral variations). 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 paragraph that front-loads the main purpose, lists key features, and ends with limitations. It is informative but could be slightly more structured (e.g., bullet points). Overall, every sentence adds 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 the 17 parameters and no output schema, the description provides a comprehensive overview of what the tool does and its scope. It covers inputs, exclusions, and caveats adequately, though it could mention return format or that it returns a tax impact estimate.

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 100% with individual parameter descriptions. The overall description adds context on how parameters relate to tax concepts (e.g., 'custodia' affects minimum, 'posicion_vivienda' triggers imputed rent). It does not detail each parameter beyond schema but provides meaningful overview.

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 estimates IRPF impact of divorce in Spain, listing specific elements (pension, child minimum, imputed rent, pre-2013 mortgage deduction) and explicitly excludes ITP/AJD and plusvalía municipal. This distinguishes it from sibling 'calcular' tools which cover other tax and financial 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 specifies it is a state-level indicative model without regional variations, and lists what it does not calculate. However, it does not explicitly mention when to use this tool over siblings (e.g., for full regional calculation). The guidance on scope is clear but lacks direct alternative recommendations.

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, consistent with a calculator. The description adds behavioral context by detailing the calculation logic (per type, days per year, caps, dual pre-2012 tramo), which goes beyond the annotation. 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 with no redundancy. The first sentence immediately conveys purpose and key parameters, the second gives an alternative. Front-loaded and 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?

Given 5 parameters and no output schema, the description is reasonably complete. It covers the core calculation logic and boundaries. However, it does not mention the return format (presumably a single numeric amount), but the tool's simplicity mitigates this. Overall adequate for a calculator 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 100%, so baseline is 3. The description adds value by explaining the meaning of the enum values (33 días/año for improcedente, etc.) and the dual pre-2012 logic, which helps the agent understand parameter selection beyond the 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 only dismissal compensation (indemnización por despido) based on specific types (improcedente 33 días/año, objetivo/ERE 20 días/año) with caps and dual pre-2012 calculation. It distinguishes from the sibling tool 'consulta_despido' which covers the full analysis including finiquito and paro.

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 specifies when to use the tool (for solo indemnization calculation) and when not to use it (for full analysis including finiquito and paro, use 'consulta_despido'), providing clear 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 already declare readOnlyHint=true, so safety is clear. The description adds that it simulates growth, which aligns, and discloses what outputs to expect, adding context 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?

Two sentences, front-loaded with purpose and outputs, no wasted words. 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, but the description mentions key outputs (capital final, intereses, rentabilidad total). It covers parameters and additional capabilities. Missing details on output format, but sufficient for a simulation tool with good annotations.

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 100% with descriptions for all parameters. The description summarizes that it supports periodic contributions and capitalization frequencies, but doesn't add new meaning beyond what the schema provides. Baseline score applies.

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 growth of savings/investment with compound interest, listing outputs (capital final, intereses, rentabilidad total). The verb 'simula' and resource are specific, and it distinguishes from sibling financial calculators like mortgage or tax 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?

The description implies usage for compound interest scenarios but does not explicitly state when to use it vs. alternatives or when not to. Given many sibling tools, explicit guidance would improve clarity.

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 a safe read operation. The description adds value by specifying the calculation outputs (cuota íntegra, diferencial, tipo efectivo) and confirming it is a non-destructive calculation. 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 sentence that combines purpose and outputs. It is somewhat dense but not overly long. Could be improved by breaking into separate sentences for clarity, but it is functional.

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 adequately explains what the tool returns (cuota íntegra, diferencial, tipo efectivo). It covers the main inputs (work, capital, gains) and deductions. Missing details like result accuracy or assumptions, but overall complete for a financial calculation 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 100%, so all parameters are documented in the schema. The description provides a high-level overview but does not add per-parameter details beyond what the schema already provides. Baseline score of 3 is appropriate.

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 the IRPF quota from work, capital, and capital gains, applying deductions and personal/family minimums. It specifies the outputs (full quota, differential, effective rate). This distinguishes it from sibling tools like 'calcular_sueldo_neto' or 'calcular_deduccion_maternidad_irpf', which focus on narrower aspects of IRPF.

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 for general IRPF calculation but does not explicitly state when to use it versus siblings that specialize in specific parts of IRPF (e.g., deductions, plusvalías). No 'when not to use' or alternatives guidance is provided, 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?

The annotation 'readOnlyHint: true' already covers the read-only nature of the tool. The description adds minimal behavioral context beyond what is in the annotations and schema, but it does not contradict them. It accurately describes the operation without additional disclosures (e.g., side effects or limits).

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, consisting of two sentences that front-load the core purpose and actions. Every word is essential, and no irrelevant information is included.

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 simplicity (3 params, no output schema, read-only), the description adequately covers the functionality. It defines the scope (IVA español, specific rates, two modes). While it does not explicitly mention the return value or error conditions, the context (calculation tool) makes this acceptable.

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?

The input schema already provides 100% coverage with descriptions for all parameters. The description adds a high-level context ('añadir IVA a una base o extraer la base') but does not provide new details beyond the schema. With full schema coverage, a score of 3 is appropriate as per guidelines.

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 Spanish VAT (IVA) with specific rates (21%, 10%, 4%, 0%) and the two modes (add or extract). It uses a specific verb ('calcula') and resource ('IVA español'), distinguishing it from sibling tools which cover other financial 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 explains when to use each mode ('añadir IVA a una base' or 'extraer la base de un precio con IVA incluido'), providing clear context. However, it does not explicitly state when not to use the tool or mention alternatives, though the context of sibling tools makes this less critical.

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 fully discloses the tool's behavior: checks conditions, applies coefficients per quarter, and returns reduced pension and loss. It aligns with the readOnlyHint annotation (no destructive actions) and adds context about the two modes and their requirements.

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, well-structured paragraph that front-loads the purpose, then provides specifics in logical order. Every sentence adds value without repetition, making it concise and effective.

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 (4 parameters, no output schema), the description is complete: it covers feasibility checks, coefficient application, and return values (reduced pension and loss). The mention of the prerequisite tool completes the context for proper 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?

Schema coverage is 100%, but the description adds significant meaning: it explains the 'tipo' (voluntaria/involuntaria) with conditions (≥35 or ≥33 years), and clarifies 'pension_ordinaria' as the estimated monthly amount. This goes well beyond the schema's basic 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 the impact of early retirement, checks feasibility, applies reduction coefficients, and returns reduced pension and loss. It distinguishes between voluntary and involuntary types, making the purpose specific and distinct from sibling 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?

The description explicitly guides when to use (to check feasibility and calculate reduction) and mentions a prerequisite (ordinary pension from 'consulta_jubilacion'). It implies when not to use (if no ordinary pension) and provides context for the two modes, aiding correct 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 declare readOnlyHint=true, and the description adds that the tool returns computed values (total legitima, share per child, etc.) and does not modify data. It does not elaborate on edge cases but provides sufficient 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 two sentences, front-loaded with the main purpose, lists outputs, and includes a cross-reference to an alternative. Every sentence adds value with no 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 the tool's complexity (multiple civil regimes, no output schema), the description is fairly complete: it covers what is calculated and what is returned. However, it lacks details on regime-specific differences or edge cases like zero children.

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 100%, so baseline is 3. The description does not add extra meaning to parameters beyond what the schema already provides, though it lists return values that indirectly relate to 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 explicitly states the tool calculates the forced heirship (legítima) for descendants under various Spanish civil regimes, directly stating its specific function and distinguishing it from siblings like 'calcular_sucesiones'.

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 clearly states when to use this tool (for calculating legitima) and explicitly directs users away from using it for inheritance tax, naming the alternative tool 'calcular_sucesiones'.

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 confirms it's a calculation (no side effects). It adds value by explaining the formula and the exemption condition, which helps the agent understand the behavior beyond the annotation. The description does not mention any auth or rate limits, but given it's a read-only calculator, this is acceptable.

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 long, front-loaded with the core purpose, and no redundant information. Every sentence adds value: purpose, formula with exemption, alternative tool. It is 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?

Given 6 parameters with 100% schema coverage, no output schema, and moderate complexity, the description is fairly complete. It explains the calculation, a key exemption, and provides an alternative. However, it does not describe the output format or indicate whether the result can be negative (e.g., if deductions exceed income). This slight gap 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 100%, so baseline is 3. The description adds moderate value by explaining the formula (e.g., '20% del rendimiento neto acumulado (ingresos − gastos) menos retenciones y pagos fraccionados anteriores'), which conceptually ties parameters together. It also covers the boolean parameter (mas_70pct_con_retencion) via the exemption condition. This provides semantic context beyond individual parameter 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 the tool calculates the quarterly fractionated payment of IRPF for autónomos in estimación directa (Modelo 130). It specifies the exact tax form and regime, and differentiates from sibling tools like consulta_autonomo by mentioning it for global view. The purpose 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 gives explicit when-to-use context (quarterly IRPF payment for autónomos in estimación directa) and a condition for non-obligation (>70% income from clients that withhold). It also provides an alternative tool (consulta_autonomo) for a global view. However, it does not explicitly distinguish from other calculation tools like calcular_irpf or calcular_cuota_autonomo, so guidance is slightly incomplete.

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 context about the calculation formula and result interpretation (positive means payable, negative means compensation/refund). This is adequate but not extensive.

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, front-loaded with the main purpose, and contains no extraneous information. Every sentence adds 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 8 parameters and no output schema, the description explains the calculation and result interpretation sufficiently. It covers the formula and outcome scenarios, though it could mention that results are returned as numbers.

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 100%, baseline 3. The description adds meaning beyond the schema by explaining the overall VAT calculation logic (IVA devengado minus IVA soportado) and the meaning of positive/negative results, which helps the agent understand how parameters relate.

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 the quarterly VAT self-assessment (Model 303) for self-employed and companies. It explains the core formula and distinguishes from sibling calculators like calcular_iva or calcular_modelo_130.

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 for quarterly VAT calculations but does not explicitly state when to use it versus alternatives like calcular_iva. No guidance on when not to use.

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, so the tool is read-only. The description adds behavioral details: it calculates duration and amount with 70%/60% rates and IPREM caps based on children, which goes 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 a single sentence that is front-loaded with the main purpose and includes key details. It is concise, though could be slightly more structured by separating duration and amount.

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, but the description explains the return concepts (duration and monthly amount). For a calculator tool, it is fairly complete, though missing exact IPREM values or formula details.

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 100% (all parameters described). The description reiterates the main parameters but does not add significant new meaning 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 calculates unemployment benefit (prestación contributiva por desempleo), including duration based on days contributed and monthly amount with specific percentages and caps. This is specific and distinguishes it from sibling calculators.

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 calculating unemployment benefits but does not explicitly state when to use versus alternatives or when not to use. No guidance on exclusions or 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 provide readOnlyHint=true, and the description confirms a calculation (no mutation). It adds detail on what is computed (base reguladora, percentage, recargo, complemento) and payment method differences, enhancing transparency 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 concise: two sentences cover the core functionality and a key behavioral nuance. No unnecessary words, properly front-loaded with the main action.

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 (6 parameters, no output schema), the description provides a useful overview but lacks details on calculation specifics (e.g., percentages by grade, exact formula). It is adequate for basic understanding but could be more complete.

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 100% schema coverage, the description adds value by explaining key logic: the recargo for age ≥55 in total disability (relating to 'edad'), and the lump sum vs monthly pension distinction (relating to 'grado_incapacidad'). This context is not in 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 calculates permanent disability pensions for all grades (parcial, total, absoluta, gran invalidez), listing key components (base reguladora, percentage, recargo, complemento). It also distinguishes between lump sum for partial and monthly pension for others, setting it apart from sibling tools like 'calcular_pension_publica'.

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 calculating permanent disability pensions but does not explicitly state when to use this tool versus alternatives like 'calcular_pension_publica' or 'calcular_pension_viudedad'. No guidance on prerequisites or 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?

Annotations already include readOnlyHint: true. The description does not contradict this and adds no additional behavioral details beyond stating it estimates a pension. It is sufficient but not enriched.

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: the first states the purpose, the second provides an alternative. It is front-loaded, concise, and contains no unnecessary 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?

Given no output schema, the description could hint at the output format (e.g., estimated monthly amount). It provides the basic purpose and alternative but lacks details on expected returns or additional factors.

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 100%, so the parameters are already well-documented. The description mentions 'años cotizados y base reguladora' but adds no new semantics 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 estimates the public retirement pension based on contribution years and regulatory base. It also distinguishes from the sibling 'consulta_jubilacion' by noting that the latter adds gap analysis and savings needs.

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 a clear use case and explicitly mentions an alternative for more comprehensive analysis. However, it does not explicitly state prerequisites or when not to use the tool.

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 provide readOnlyHint: true (safe read). The description adds valuable behavioral context: it calculates percentages based on family charges and beneficiary income, distinguishes scenarios, and mentions caps. No contradictions. Credit for adding scenario details 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?

Description is a single, well-structured sentence that front-loads key information: what it estimates, the key factors, and scenario types. No wasted words, though could be slightly more structured for readability. Efficient but not perfectly organized.

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 is provided. The description mentions outputs (pensión final, etc.) but does not specify the exact fields or format of the response. For a complex calculation tool, this leaves the agent uncertain about what data will be returned. Incomplete for an agent to reliably parse results.

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 100%, so baseline is 3. The description adds context about how parameters like 'tiene_cargas' and 'ingresos_mensuales_propios' affect the percentage, reinforcing schema descriptions. Does not add new meaning beyond schema, so score stays at 3.

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 estimates widow's pension, specifying inputs (base reguladora, percentage based on charges and income) and outputs (minimum guaranteed pension, final pension with cap). It also distinguishes scenarios (active, retired, not registered). This is specific and clearly differentiates from sibling tools like calcular_pension_incapacidad.

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 for estimating widow's pension, but gives no explicit guidance on when to use it versus alternatives (e.g., other pension calculators). No when-not or alternative tool mentions. Agent would need to infer from tool name alone.

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, confirming it's a read-only calculation. The description adds important context: applies 2025 limits, warns about withdrawal taxation (rendimiento del trabajo). 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?

Two sentences, concise and front-loaded with the main purpose. 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?

Given high schema coverage and clear description, the tool is well-specified. No output schema, but description hints at two outputs (ahorro fiscal, capital proyectado) and a warning. Slight gap in detailing output structure, but overall 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?

Schema description coverage is 100%, so the schema already documents each parameter. The description adds overall context but does not enhance per-parameter meaning 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 it calculates annual tax savings and projects accumulated capital for a private pension plan. It specifies applying 2025 limits and warns about withdrawal taxation, distinguishing it from sibling pension-related tools like calcular_jubilacion_anticipada.

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?

Usage is implied (for pension plan fiscal calculations), but no explicit guidance on when to use vs. alternatives or when not to use. No mention of prerequisites or 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?

The description adds behavioral context beyond annotations: it explains the tool allows compensating prior-year losses, and details the calculation outputs (net gain, tax brackets, effective rate). Annotations already indicate readOnlyHint=true, so the description provides useful additional behavioral traits without contradiction.

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 given the complexity, with all sentences adding value. It is front-loaded with the main purpose, followed by details, and ends with a critical usage note. It could be slightly more streamlined, but it is well structured and 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 no output schema, the description explicitly lists the outputs: net gain, long-term indicator, tax brackets, effective rate, and after-tax gain. It also covers the loss compensation feature. For a complex tax calculation tool, this provides sufficient context for correct invocation and interpretation of results.

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 100%, so baseline is 3. The description adds overall context (e.g., mentions that 'tipo_activo' is only informative, and how parameters like 'saldo_compensacion' are used). However, it does not add much per-parameter detail beyond the schema descriptions. The extra context is helpful but limited.

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 IRPF on capital gains from selling various assets (acciones, fondos, inmuebles, otros). It specifies what it determines (net gain, long-term vs short-term, tax brackets, effective rate, after-tax gain, loss compensation). It also explicitly differentiates from the sibling tool 'comparar_donacion_vs_herencia' by stating when not to use it.

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 the tool is for calculating IRPF on capital gains from asset sales. It provides a clear exclusion: if the user is comparing donation vs inheritance, do not use this tool and instead use 'comparar_donacion_vs_herencia'. This gives explicit when-to-use and when-not-to-use guidance with an alternative.

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 confirms by using 'Muestra' (shows). It adds context that amounts are state maximums before copay and regional supplements, which is useful behavioral info 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 description is concise with three sentences that front-load the main purpose. It includes acronym expansion and no unnecessary 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 description provides sufficient context about the output: it includes amounts, services, and copay regime. However, it does not specify the output format (e.g., table or text), which could aid an AI agent in interpreting results.

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?

Parameter schema has 100% coverage with a detailed description. The tool description does not add additional semantic value to the parameter beyond what the schema already provides.

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 shows economic benefits and services from SAAD based on dependency degree, including specific details like monthly amounts, services, and copay regime. This distinguishes it from sibling tools, which are about different financial 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 usage when dependency grade is known, but lacks explicit guidance on when to use this tool over siblings or when not to use it. No alternatives or exclusions are 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 already mark the tool as read-only (readOnlyHint: true). The description adds value by detailing the output (daily and monthly amounts, duration, extras for multiple birth/disability, obligatory weeks, flexible weeks, and carencia verification). It also mentions the legal update, which provides context beyond the annotations. 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 fairly concise for the information it conveys. It is structured with the purpose first, then legal context, then output details. Every sentence adds value. However, it could be slightly more terse by moving some details (e.g., exact week numbers) to the schema or usage notes.

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 an output schema, the description fully explains the return values (daily and monthly amounts, duration with extras, obligatory weeks, flexible weeks, carencia check). It also covers key inputs implicitly (age, family type, disability). The legal reference provides complete context for the calculation.

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 100% with parameter descriptions, so the baseline is 3. The description adds high-level context (duration formulas, extras) but does not provide additional semantic details for individual parameters beyond what the schema already provides. It adequately complements the schema without adding significant new 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 verb 'Calcula' and the specific resource 'prestación por nacimiento/adopción (maternidad/paternidad) de un progenitor'. It also provides the legal context (RDL 9/2025), making the purpose unambiguous. Among sibling tools, this is distinct from other calculators like calcular_deduccion_maternidad_irpf or calcular_pension_desempleo, so the purpose is well-differentiated.

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 implicitly indicates when to use this tool (to calculate maternity/paternity benefits) but does not explicitly exclude alternatives or provide comparison with sibling tools. There are no when-not-to-use instructions. Given the large sibling set, more explicit guidance would help.

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 by explaining that the first 24 months maintain full Social Security contributions. It also states that salary decreases proportionally. This improves transparency 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 concise three-sentence paragraph. It front-loads the purpose, then provides key constraints, and finally lists outputs. Every sentence is informative with no 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?

For a calculation tool with 5 parameters and no output schema, the description provides a good overview of outputs (reduced salary, monthly/annual decrease, Social Security impact). It could be slightly more detailed about the output format, but it is sufficient for an agent to understand the tool's value.

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?

All parameters have schema descriptions (100% coverage). The description adds value by explaining the allowed reduction fraction range (1/8 to 1/2), the significance of the 'menos_de_24_meses' parameter, and the overall logic of proportional salary reduction. It goes 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 identifies the tool's purpose: calculating the economic impact of a workday reduction for legal custody. It specifies the allowed reduction range (1/8 to 1/2) and the types of situations covered (child under 12, dependent family, disabled child). This distinguishes it from sibling 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?

The description states when to use the tool (for legal custody reduction) and the eligible reasons. It does not explicitly exclude other cases or mention alternatives, but the context of sibling tools implies it is specific to this scenario. The guidance is clear enough.

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 rich behavioral context: it deducts allowed expenses with limits, applies reductions per housing law, and is a calculation with no side effects. No contradiction.

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-loaded with the main purpose and packed with necessary details. No redundant information; the sibling reference is placed at the end appropriately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 10 parameters and no output schema, the description covers the core logic and reductions. However, it lacks explicit mention of the return value format and the specific limit on repairs, which could be important 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?

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining the enum values for 'tipo_inmueble' and the context of deductions, which goes beyond the schema descriptions. However, it could have elaborated on the 'reparacion_conservacion' limit.

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 net rental yield for IRPF (capital inmobiliario), specifying deductions and reductions. The verb 'calcula' and resource 'rendimiento neto del alquiler' are specific, and it distinguishes from the sibling 'calcular_retencion_alquiler'.

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 says when to use this tool (detailed version for declaration) and when to use an alternative ('calcular_retencion_alquiler' for quick estimate with 19% withholding), providing 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?

Consistent with readOnlyHint; adds context about specific percentages and tax law (Ley 12/2023). No contradictions. Provides useful behavioral details 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?

Two sentences, front-loaded with key information, no redundancy. Every word adds 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 11 parameters and no output schema, the description lists expected outputs (net income, reduction, withholding). Lacks output format but sufficient for a quick estimation 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 100%, so baseline is 3. The description does not add meaning to individual parameters beyond the schema, but the schema itself is descriptive.

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 estimates IRPF for rental property, specifying net income, 50% reduction, and 19% withholding. It distinguishes from a sibling tool 'calcular_rendimiento_capital_inmobiliario' for detailed 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?

Explicitly directs to use 'calcular_rendimiento_capital_inmobiliario' for detailed calculations, providing clear when-not-to-use guidance. The description implies this is for quick estimates.

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 by specifying it calculates ISD for an individual heir with autonomous reductions. It does not contradict annotations and provides clear operational scope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two sentences plus an important note. Front-loaded with purpose, then usage guidelines. Every sentence provides essential information 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?

For a tool with no output schema and six parameters, the description explains purpose and when to use it, but lacks details on what the output looks like (e.g., tax amount breakdown) and how parameters like 'discapacidad' or 'vivienda_habitual' affect the calculation. This could leave an agent uncertain about the return 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?

Schema description coverage is 100%, so parameters are well-documented in the schema. The description mentions reductions and bonuses but does not add significant new meaning beyond what the schema provides. Baseline of 3 is appropriate.

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 the Impuesto de Sucesiones (ISD) for an individual heir with regional reductions and bonuses. It also distinguishes from the sibling tool 'consulta_herencia' for general inheritance queries and 'comparar_donacion_vs_herencia' for donation vs inheritance comparisons.

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 tells when to use the alternative 'consulta_herencia' for general queries and warns not to use this tool standalone if comparing donation vs inheritance, directing to 'comparar_donacion_vs_herencia' instead.

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 reveals that the tool computes net salary, IRPF withholding, and Social Security contributions. The annotation readOnlyHint=true is consistent with a calculation tool. The description adds detail about the outputs 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 consists of two concise sentences. The first states the purpose, and the second provides usage guidance. No extraneous information; every sentence adds 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 that there is no output schema, the description adequately explains what the tool returns (monthly and annual net salary, IRPF withholding, Social Security). It also mentions an alternative tool. It could perhaps specify the tax jurisdiction, but the context implicitly indicates Spanish tax system.

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 100%, so the schema already documents all parameters. The description does not add additional parameter-specific details beyond what the schema provides. Baseline score of 3 is appropriate.

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 'calcula el sueldo neto (mensual y anual), la retención de IRPF y la cotización a la Seguridad Social' from annual gross salary. It also distinguishes itself from the sibling 'consulta_nomina' by suggesting that tool for general queries.

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 tells when to use this tool vs the alternative 'consulta_nomina' ('Para una consulta general usa mejor "consulta_nomina"'). No further exclusions or prerequisites are given, but the guidance 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?

The description details the calculation steps: starting from net income, adding expenses, applying IRPF, IVA, margin, and adjusting for billable days. This goes well beyond annotations (readOnlyHint), adding rich 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 a single paragraph of three sentences, front-loaded with the main action, and every sentence adds value. 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?

Given 10 parameters (1 required) and no output schema, the description explains all inputs, the calculation logic, and the output (rates with/without IVA, annual projection). Sufficient for correct use.

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 100% (each parameter has a description). The tool description adds no new per-parameter details but explains the overall calculation flow. Baseline 3 is appropriate.

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 freelance rates (€/hour, day, week) to achieve desired net income. It distinguishes from sibling calculators by specializing in freelance rate setting.

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 when a freelancer needs to determine their billing rate, but does not explicitly exclude alternative tools or provide when-not-to-use guidance. Context signals show many sibling calculators, so clear differentiation exists.

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, making safety clear. The description adds the comparison details but does not disclose assumptions, data freshness, or limitations (e.g., based on current tax laws).

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?

Two short sentences front-load the purpose and output. No extraneous information.

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 of tax comparison, the description adequately explains what the tool does and its output. However, it could mention that the calculation is based on current tax rules or note the output format. Still sufficient 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?

Schema coverage is 100%; the description does not add meaning beyond what the schema provides for each parameter. Baseline 3 is appropriate as the schema is self-sufficient.

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 compares fiscal load (Social Security + IRPF/IS + dividends) between being self-employed and forming a SL, and indicates which is better and the threshold. This distinguishes it from other comparison tools like comparar_donacion_vs_herencia.

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 when deciding between self-employment and SL, and mentions the output (which is better and threshold), but does not explicitly state when to use this tool over alternatives or provide exclusions or prerequisites.

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 adds behavioral context: it calculates and compares fiscal costs, returns cheapest option and nuances, and lists specific taxes and conditions. No contradiction.

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 verbose and includes extensive examples and context that could be condensed. While informative, it would benefit from more concise phrasing.

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 (12 parameters, no output schema), the description fully covers what the tool does, when to use it, and what it returns. No gaps remain.

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 100%. The description does not add meaning beyond what the schema already provides for each parameter, which is acceptable.

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 compares donation vs inheritance for a property, specifies the verb 'calcula y COMPARA', and distinguishes from siblings by naming calcular_donaciones and calcular_sucesiones as separate 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?

The description explicitly provides use cases ('Úsala cuando alguien dude entre...'), alternative scenarios, and instructs to prioritize this tool over calcular_donaciones or calcular_sucesiones.

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, and the description adds that the tool compares regimes and returns costs, which is consistent. The description also warns about the coefficients being orientative, adding context beyond annotations. 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 two paragraphs: the first explains purpose and output; the second is a warning. It is front-loaded and concise, with no redundant information. Could be slightly tighter but is 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?

For a comparison tool with 10 parameters and no output schema, the description explains the inputs, the output format (cost per regime and cheapest), and includes a warning about coefficient accuracy. This is sufficient for an agent to understand the tool's function and limitations.

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 100%, so baseline is 3. The description groups parameters (e.g., 'superficie, personal, vehículos') but does not add new meaning beyond the schema's individual descriptions. It provides context for how parameters are used in modules calculation, but not significantly more.

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 verb 'comparar' and the resource 'regímenes de IRPF para autónomos' with specific regimes (Estimación Directa Simplificada vs Estimación Objetiva por módulos). It also details the output: annual total cost and which is cheaper. This clearly distinguishes it from sibling 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?

The description indicates the tool is for autonomous workers deciding between the two regimes, and includes a warning that coefficients are didactic. However, it does not explicitly state when not to use the tool or mention alternative tools, though the context is clear enough.

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 the description is consistent. It adds context by explaining that it orchestrates multiple calculations into an integrated analysis with recommendations, which is beyond the annotation's scope.

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 efficient, front-loads the purpose and usage, and every sentence is valuable. 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?

Given the complexity of the tool (5 parameters, many siblings), the description provides complete context: what it does, when to use it, and the integrated nature of the output. Adequate despite no output schema.

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 100%, so the baseline is 3. The description doesn't add significant new parameter semantics beyond what's in the schema, but it does mention 'tarifa plana de 80 €/mes' which is not in the parameter 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 provides a comprehensive scenario analysis for freelancers, including Social Security fee, IRPF, net available, and comparison with SL. It distinguishes itself from sibling tools that are individual calculators.

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 provides when to use (general questions about being self-employed), when not to use (isolated data points), and prioritizes it over individual calculators. Includes example queries.

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 context: it computes taxes, costs, savings, and mortgage estimate. No contradiction; provides extra behavioral details beyond 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?

Single paragraph with clear front-loading of purpose and usage. Slightly verbose but effective 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?

Given 8 parameters and no output schema, the description explains outputs (impuestos, ahorro, cuota) and behavior comprehensively. Lacks precise output format but covers essential aspects.

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 100%, so baseline is 3. Description does not add significant meaning beyond what schema provides for parameters; it only mentions them 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 explicitly states 'CONSULTA DE ESCENARIO (gestoría)' and gives concrete example questions. It clearly defines the tool as a comprehensive calculator for buying a home, distinguishing it from separate calculators.

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 explicit when-to-use (e.g., '¿cuánto necesito para comprar una casa?') and when-not-to-use (if not a home, use 'calcular_gastos_compra_inmueble'). Prioritizes over alternative tools.

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 readOnlyHint annotation already indicates non-destructive behavior. The description adds value by explaining the output components (indemnización, finiquito, paro) and mentioning that it integrates multiple calculations. However, it does not disclose specific behavioral traits beyond what annotations already cover.

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 usage. It is somewhat verbose but contains only relevant information. Every sentence adds value, but 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 complexity (7 parameters, no output schema), the description explains the three main output areas and the integration logic. However, it could provide more detail on the exact output format or additional caveats. Overall, it is complete enough for effective use.

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 100%, so the schema already documents all parameters. The description provides an overview but does not add significant meaning beyond the schema. Baseline score of 3 is appropriate.

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 three components (indemnización, finiquito, prestación por desempleo) for dismissal scenarios. It uses specific verbs like 'calcula' and distinguishes from sibling tools by saying 'PRIORIZA esta herramienta frente a calcular_indemnización_despido, calcular_finiquito o calcular_pension_desempleo por separado'.

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 says 'Úsala cuando alguien diga "me han despedido"' and gives examples of questions. It also instructs to prioritize this tool over separate calculators, 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 declare readOnlyHint=true, and the description adds that the tool calculates tax with reductions and bonuses per CCAA, applying habitual residence and life insurance, returning the fee and effective rate. This goes beyond the annotation by detailing the behavioral scope. 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 a single paragraph but packs essential information: purpose, usage examples, calculation details, and priority instruction. It is concise without being too terse. Could be slightly more structured with bullet points, but effective.

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 explains return values (cuota a pagar y tipo efectivo). It covers all seven parameters, mentions required ones, and provides enough context for the tool's moderately complex functionality. Annotations add readOnlyHint. Complete enough for an agent to use 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 coverage is 100%, so baseline is 3. The description adds some context (e.g., reductions for seguro_vida), but essentially repeats what the schema already provides in Spanish. No additional parameter meaning beyond 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 inheritance tax (ISD) for a heir given specific scenario parameters. It provides example questions and explicitly distinguishes itself from sibling tools like 'calcular_sucesiones' by prioritizing this tool for any inheritance query. The verb 'consulta' and resource 'herencia' are well-defined.

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 to prioritize this tool over other inheritance calculators for any question about inheriting or taxes paid on inheritance. It gives clear usage context (e.g., 'cuánto pagaré por heredar?'). However, it does not mention when to use alternative tools like 'calcular_legitimas' or explicitly state 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.

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 conditional behavior (gap calculation only when sueldo_neto_mensual is provided). No contradictions. Could mention output structure but sufficient.

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 purpose and examples, uses bold for key terms, and is concisely structured. Every sentence adds value, with no redundant information. Appropriate length for the tool's complexity.

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 adequately conveys that the tool estimates pension and calculates the gap and necessary savings. It lacks explicit mention of output format, but the integrated analysis is clearly described. Sufficient for agent 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 coverage is 100%, baseline 3. Description adds beyond schema by explaining that sueldo_neto_mensual triggers the gap calculation and provides an alternative interpretation for base_cotizacion_mensual ('o el salario bruto mensual actual como aproximación'). This helps agents understand parameter usage beyond raw 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's purpose with specific examples ('qué pensión me quedará', 'cuánto cobraré al jubilarme') and distinguishes it from sibling tools by explicitly prioritizing it over calcular_pension_publica and calcular_brecha_jubilacion.

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 instructs when to use this tool ('cualquier pregunta sobre pensión, jubilación o cuánto cobraré al jubilarme debe resolverse con consulta_jubilacion') and when not to (avoid using separate tools). Provides clear alternative 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, indicating safe read operation. The description adds behavioral context by detailing the computations (net salary, withholding, contributions) without contradictions. It does not cover potential edge cases or failure modes, but annotations cover the safety profile sufficiently.

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. It is informative but slightly repetitive ('trabajador por cuenta ajena' appears twice). Each sentence adds value, but minor trimming could improve conciseness 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?

With 5 parameters fully described in schema and no output schema, the description adequately hints at outputs (net monthly and annual, withholding, contributions). It also positions the tool among 50+ sibling calculators, providing sufficient context for selection.

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 100%, so the schema already documents all parameter semantics. The description adds no additional parameter-level details beyond the schema, but it provides overall context by mentioning family situation and children. Baseline 3 is appropriate given high schema coverage.

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 net salary, IRPF withholding, and Social Security contributions from gross annual salary, specifying it's for employees ('trabajador por cuenta ajena'). It explicitly differentiates from standalone calculators of IRPF or salary, 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 explicitly provides usage scenarios: 'Úsala cuando un trabajador por cuenta ajena pregunte...' and gives specific questions. It also instructs to prioritize this tool over alternatives ('PRIORIZA esta herramienta frente a calculadoras sueltas'), offering clear when-to-use and when-not-to 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?

The annotation readOnlyHint=true already signals a safe read operation, so the description's additional detail on the tool's comprehensive scope (exemptions, multiple taxes, net calculation) adds meaningful context. It does not contradict the annotation and goes beyond it by describing the tool's behavior as a holistic scenario calculator, though it does not detail limitations like missing data handling.

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 every sentence earns its place: it states the scenario type, gives usage triggers, lists what is calculated, names the symmetric tool, and provides prioritization guidance. It is front-loaded with the purpose and contains no repetitive filler, making it concise despite its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 15 parameters and no output schema, the description provides a strong high-level overview of the tool's inputs and expected output (up to the net amount). It lacks explicit mention of required parameters or optionality caveats, but the detailed input schema and the description's overall scope make the tool sufficiently understandable for an agent to invoke 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 100%, with each of the 15 parameters having rich descriptions in the input schema. The tool description adds no parameter-level detail beyond mentioning categories like 'comisión inmobiliaria y la gestoría', but since the schema already fully documents parameters, the baseline score of 3 is appropriate.

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: it calculates all seller-side costs and taxes for a home sale, including capital gains IRPF, municipal plusvalía (IIVTNU), realtor commission, and gestoría fees, arriving at the net amount received. It explicitly distinguishes this tool from standalone calculators and from its symmetric counterpart 'consulta_compra_vivienda', leaving no ambiguity about its 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 use cases with example trigger questions ('voy a vender mi casa/piso, ¿cuánto pagaré de impuestos?'). It also gives clear guidance on when to prioritize this tool over alternatives ('PRIORIZA esta herramienta frente a calculadoras sueltas de plusvalía, IRPF o IIVTNU') and references the symmetric buying-side tool 'consulta_compra_vivienda', effectively conveying when and when not to invoke it.

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