Cálculo de Pensão Alimentícia

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

Annotations only convey idempotent=true, not-read-only, and not-destructive; the description adds genuinely useful behavioral detail: config-based tokens produce a permanent non-expiring connection while pasted tokens are session-only, and no-args invocation returns a link. It doesn't mention whether existing sessions get invalidated, but there is no contradiction with 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?

At roughly 65 words it is compact, but the structure is poor: it reads like chat support text ('Best: ... Or ...') and buries the agent-relevant invocation contract at the end after branding and human setup instructions. The front-loaded content serves the human user, not the agent selecting the tool.

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 simple tool (1 optional parameter, no output schema, no nested objects), the description covers invocation modes, token format, and persistence semantics. The main gap is not clearly stating what the tool returns in each mode beyond the implied link, and no mention of error behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for the single 'token' parameter. It explains that token is a JWT pasted by the user and that omitting it triggers link generation — meaningful compensation. It falls short of 5 by not clarifying return values or invalid-token behavior.

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 identifies the resource (authentication for MCP.AI/IDE agents) and the two core behaviors: returning a login link when called with no args, or accepting a pasted JWT token for session login. It is reasonably distinguishable from the unrelated calculo_* siblings, though it opens with awkward branding and human instructions rather than a crisp verb+resource statement.

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 contrasts the two auth strategies — permanent config header vs session-only token paste — and states precisely when to call with a token ('after the user pastes') vs without args ('to get the link'). It gives clear conditional context but stops short of naming alternatives or when-not-to-use among siblings.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds behavioral context: it reveals the tool performs a calculation (no side effects), returns monthly breakdown plus total, and applies a legal formula. It also says it corrects overdue months to the current date, which is non-obvious. This exceeds baseline given annotation coverage.

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 high information density. It front-loads the legal basis and outcome, then lists the exact variables and return value. No filler or 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 9-parameter calculator with no output schema and 0% schema coverage, the description conveys the core algorithm and output shape. However, it does not explain how optional params (juros, multa, indice, periodicidade_meses, data_calculo) alter the calculation when omitted, and it doesn't mention whether indices rates are fetched internally or must be supplied. The main purpose is clear, but edge cases around optional parameters are not fully covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden for parameters, but it only names general concepts: aluguel_inicial, inicio_contrato, inicio_atraso, fim_atraso, juros, multa, indice. It does not specify formats (ISO dates?), how optional params behave, or which combination of fields is required. The required fields are obvious from names, but the semantics of juros/multa/indice/periodicidade_meses could benefit from more explicit definitions.

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 a specific verb 'calcula/reajusta' with a specific resource (aluguéis em atraso) and cites the legal basis (Lei 8.245/91). It lists the applicable adjustments (índice, juros de mora, multa moratória) and what it returns (detalhamento por mês + total). 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 implies usage for overdue rent calculations under Lei 8.245/91, and the detail about applying index adjustments, late fees, and interest makes it clear. It does not explicitly tell when not to use it or point to alternatives like calculo_atualizar or calculo_indice, but the context is sufficiently clear for a domain-specific calculation 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 convey read-only, idempotent, and non-destructive behavior; the description adds that it corrects installments, applies interest/fine/fees, and returns a per-installment breakdown and totals. It also discloses important legal traps. 'Atualização' here means monetary correction, not a mutation, so there is no contradiction with readOnlyHint.

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

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

Three dense sentences with no filler: purpose, output, then critical caveats. The front-loaded warning about SELIC and IPCA legal regime earns its place because it prevents a common calculation error.

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 an 11-parameter tool with no output schema and no parameter descriptions, the description is largely complete: it gives the domain, the input concepts, the return shape, and the legal regimes that control valid invocations. It could still detail how ABATIMENTO_PAGAMENTO is treated and what the default option values are, but the essential information to select and invoke the tool correctly is present.

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 zero schema descriptions, the description supplies the missing semantics for the most important parameters: 'índice oficial' maps to indice; 'juros, multa e honorários' map to their corresponding fields; 'parcelas' is the required array. It also tells the agent how legal rules should affect parameter choices. Some parameters (pro_rata, multa_incide_sobre_juros, honorarios_tipo) are not individually explained, but the core invocation is covered.

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 names the exact calculation: 'Atualização monetária / liquidação de débito judicial' and specifies the operation 'corrige parcelas por um índice oficial', followed by juros, multa and honorários. It also states the return shape (detalhamento por parcela e totais), making it distinguishable from sibling calculo_* tools at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: judicial debt settlement. The legal-regime warnings are actionable guidance for configuring indice, juros, and taxa_juros (SELIC already includes correction plus interest; post-September/2024 civil uses IPCA + legal rate). It does not explicitly name excluded sibling tools, so it stops one step short of a full when-not-to-use statement.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safe, non-mutating nature. The description adds meaningful behavioral context by explaining the three-phase calculation method and that fractions are configurable, which helps the agent understand what the tool actually computes.

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 compact, front-loaded with the core purpose, and each sentence adds domain-specific detail. There is no repetition or 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?

For a tool with 9 parameters, no output schema, and no parameter descriptions, the description is too high-level. It omits expected input units/ranges, the meaning of the required penalty range parameters, and what the result looks like, leaving the agent to guess crucial invocation 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?

With 0% schema description coverage, the description carries the full burden of explaining parameters, but it only maps broad conceptual phases to categories like atenuantes/agravantes and causes of increase/decrease. It does not clarify the meaning of required fields pena_min_anos/pena_max_anos, the numeric format for fractions (decimal vs percentage), or how the arrays should be structured.

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 identifies a specific legal computation — criminal sentence calculation under the three-phase system of art. 68 CP — with concrete references to art. 59, Súmula 231 STJ, and causes of increase/decrease. This clearly distinguishes it from sibling tools like calculo_fgts or calculo_aluguel.

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 criminal sentencing dosimetry, so an agent can infer when to use it. However, it does not explicitly state when to prefer this over alternatives or mention any excluded scenarios, such as prison progression (calculo_progressao).

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context such as per-deposit processing, 3% a.a. interest, and the current limitation to manual deposits ('Aceita depósitos manuais'), but it does not disclose output format, error conditions, or other limitations.

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 efficiently front-loaded: the first sentence captures the resource, calculation, and interest rate, and the second adds the input mode. The parenthetical future OCR note is a minor non-essential detail, but not distracting enough to be a serious flaw.

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 4-parameter tool with no output schema and no property descriptions, the description gives a solid high-level overview but omits critical invocation details such as the meaning/format of data_calculo, the format of competencia, and the default/enum behavior of indice. The read-only and idempotent annotations reduce some burden, but the agent still cannot fully infer the required call structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description partially compensates: it maps 'índice de inflação' and 'TR' to the indice parameter, directly references depositos, and the 'juros de 3% a.a.' phrase clarifies incluir_juros_3aa. However, data_calculo is never mentioned, and the exact format of competencia or the default behavior of indice are not addressed.

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 states a specific verb and resource: 'Correção do FGTS' with 'por depósito calcula a diferença entre corrigir pelo índice de inflação vs pela TR'. It names the exact legal thesis (TR → INPC/IPCA-E, STF) and clearly distinguishes this tool from the sibling calculo_* 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 the usage scenario — correcting FGTS deposits against inflation indices vs TR — but never explicitly contrasts it with alternatives like calculo_revisional or calculo_trabalhista. There is no when-to-use/when-not-to-use guidance, leaving routing to inference.

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 establish read-only and idempotent behavior. The description adds useful behavioral context beyond that: the month exclusion/inclusion convention and the conditional return modes depending on `valor` and `incluir_valores`. No contradiction with annotations exists.

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 compact and front-loads the main purpose before diving into optional behavior. The clauses are dense but every part adds information. It is slightly run-on due to the parenthetical convention note, but overall well-sized.

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 core use case and optional outputs, but with no output schema and no parameter descriptions, it leaves gaps: `pro_rata` is undocumented, `data_final` optionality/default is not stated, and the exact return shape is vague. It is adequate, but not complete for a 6-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate, and it partially does: it explains the meaning and effect of `valor`, `incluir_valores`, and the date-range convention. However, `pro_rata` is left completely unexplained, and date format/default behavior for `data_final` is not addressed.

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 names a specific resource ('índice oficial') and a specific action ('fator de correção acumulado entre duas datas'), with the BACEN/IBGE convention clearly stated. This distinguishes it from sibling calculation tools like calculo_aluguel or calculo_fgts without needing to open their schemas.

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 clear functional context: it is the tool for official index correction factors between two dates. It also explains the two optional behaviors based on `valor` and `incluir_valores`. It does not explicitly name alternatives or exclusion criteria, but the purpose is specific enough that an agent can infer when 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?

As anotações já indicam readOnlyHint, idempotentHint e destructiveHint false, então o perfil de segurança está coberto. A descrição agrega contexto comportamental relevante ao explicar a fórmula (bens − dívidas conforme o regime), o cálculo de quotas e a possibilidade de override via entra_partilha. Não contradiz as anotações.

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

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

A descrição é curta, direta e bem estruturada: a fórmula vem primeiro e a instrução de override vem em seguida. Não há palavras desnecessárias nem repetição do nome da ferramenta.

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

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

A descrição cobre os insumos principais e o conceito do resultado, mas não descreve a forma do retorno nem detalha como cada valor do enum regime afeta o default de inclusão dos bens. Dado que não há output schema e há objetos aninhados complexos, a definição ainda deixa lacunas relevantes para uma invocação totalmente precisa.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Com 0% de cobertura descritiva no schema, a descrição precisa compensar e compensa parcialmente: explica bem o papel de regime, bens, dívidas e entra_partilha. Contudo, deixa sem explicação campos importantes dos objetos aninhados, como titular, oneroso, incomunicavel, heranca_doacao, adquirido_na_constancia, anterior_casamento e nomes, o que pode dificultar a construção correta da entrada.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

A descrição identifica de forma específica o recurso ('partilha de bens no divórcio por regime') e o verbo 'apura' indica exatamente o que é calculado: massa partilhável, quota de cada cônjuge e torna por desequilíbrio. Isso diferencia claramente a ferramenta dos irmãos calculo_pensao, calculo_revisional e outros, que tratam de contextos distintos.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

A descrição estabelece contexto claro de uso: partilha de bens no divórcio conforme o Código Civil e conforme o regime de bens. Também orienta o agente a marcar entra_partilha para sobrepor o default do regime. Não há, porém, exclusões explícitas ou comparação com alternativas, então não chega a 5.

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

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

The description discloses the full calculation flow: monthly amount by mode, subtraction of payments, INPC correction, and 1% monthly interest from each due date. This adds meaningful behavior beyond the annotations, though it does not mention that the index or interest rate can be customized via the optional indice/juros parameters.

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

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

One information-dense sentence with no filler or repetition. The subject and legal article are front-loaded, followed by the calculation steps in a compact, readable sequence.

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 adequate for a read-only calculator with safety annotations, but it does not describe the output format and leaves 'data_calculo' unexplained. Since there is no output schema, the agent still has a clear gap in knowing what the tool returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries the burden, and it does: it explains the three 'forma' modes, payments, remuneration percentages, correction index, and interest. It leaves 'referencia' and 'data_calculo' somewhat implicit, but an agent can infer their roles from the described formula.

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 names the exact resource ('Pensão alimentícia em atraso') and legal basis (art. 528 CPC), then states the specific computation performed. This makes it immediately distinguishable from the sibling calculation tools, which target other domains such as labor, FGTS, aluguel, or INSS.

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 phrase 'Pensão alimentícia em atraso' implies when the tool applies, but there is no explicit guidance about when to choose this over alternatives or when not to use it. The description identifies the context but does not compare it with sibling 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint:false, so the safety profile is covered. The description adds behavioral context by describing how the percentage is computed (primário/reincidente, comum/hediondo, violência/resultado morte) and that remição and detração are deducted before returning the progression date. It does not disclose output structure or edge cases, but the core behavior is visible.

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

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

One dense sentence front-loads the legal basis and calculation logic and stops after the output. Every clause adds information, with no filler or repetition of the schema.

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 9-parameter calculator with no output schema, the description is adequate but incomplete: it states the main factors and the returned value, but omits the output format, date input format, and any limitations or assumptions about the legal requisitos. An agent would need to inspect parameter names or make reasonable guesses.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates by mapping the parameters to legal concepts: reincidente, hediondo, violencia, resultado_morte, horas_estudo/dias_trabalhados (remição), and detração. However, it does not explicitly explain the date format for inicio_cumprimento or the exact meaning of every numeric parameter, leaving some inference to the property names.

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 names the specific legal calculation (prison regime progression under LEP art. 112, Lei 13.964/2019), identifies the relevant factors, and states that it returns the progression date. This clearly distinguishes it from sibling calculators like calculo_dosimetria or calculo_trabalhista.

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 intended scenario is strongly implied by the legal reference and formula, but there is no explicit when-to-use/when-not-to-use guidance or comparison with sibling tools. An agent would have to infer that it is for progressão de regime rather than, say, dosimetria da pena.

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, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond this: it sums corrected installments, is restricted to specific codes, and is framed as an administrative rather than judicial remedy. There is 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 two concise, information-dense sentences. It front-loads the core function and scope, then adds the legal context. No word is wasted.

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 purpose, applicable codes, and legal framework, but it does not explain the correction index parameter or calculation date, and there is no output schema to clarify the return value. For a 3-parameter tool with no parameter descriptions, this is adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It partially explains descontos as the discounted installments to be summed and hints at valid codes, but it does not explain the 'indice' parameter's role in correction or what 'data_calculo' means. This is a meaningful gap given the lack of 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 a specific function: calculating restitution of undue INSS discounts by summing corrected installments. It further narrows scope with specific codes (280/304/310/378) and the STF agreement context, making it distinguishable from sibling tools like calculo_revisional or calculo_fgts.

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 for when to use the tool: cases of undue INSS discounts from associative fraud with the listed codes, under the administrative reimbursement route via the STF agreement. It does not explicitly name alternative tools or give when-not-to-use guidance, so it falls short of a 5.

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 meaningful behavioral context beyond the annotations by disclosing the live BACEN lookup by modality+month and the legal caveat that the average rate is a reference, not a ceiling (STJ). The annotations already declare readOnlyHint and idempotentHint, and the description does not contradict them.

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 dense sentences carry the core domain, calculation logic, and a legal nuance with no filler. The most important disambiguating phrase ('Revisional de contrato bancário') is front-loaded.

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 core calculation and the output concept ('excedente por parcela'), and annotations cover safety. But with 8 parameters, 0% schema descriptions, and no output schema, it leaves the agent to infer exact return shape, optional parameter behavior, and parameter-level semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It partially does by linking modalidade+mês to the live rate lookup and Price/SAC to the payment system, and by implying parcela_paga relates to the excess calculation. However, it does not clarify units, optional parameters like taxa_bacen_am, data_contrato's role, or defaults for sistema.

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 uses a specific verb ('recalcula') and resource ('financiamento') and clearly identifies the domain as 'Revisional de contrato bancário'. It also names the BACEN average-rate recalculation and per-installment excess computation, which set it apart 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 phrase 'Revisional de contrato bancário' gives clear context for when to use this tool, and the mention of Price/SAC systems and BACEN live lookup helps disambiguate from other calculo_* siblings. It does not explicitly state when not to use it or name alternative tools, but the domain context is strong.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds useful computational context about the 5% limit and corrected restitution, but it does not describe return structure or error behavior. There is 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 two dense sentences with no filler. The most identifying details (RMC/RCC, INSS, 5% limit, restitution) are front-loaded, and the legal thesis sentence adds domain context 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 calculation tool with five parameters, 0% schema coverage, and no output schema, the description is not complete enough. It explains the domain but not how to construct the inputs, what the output represents, or how to choose tipo and indice, leaving substantial inference burden on the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description should compensate for the five parameters. It only alludes to 'descontos' and indirectly to a correction index via 'restituição corrigida'; it does not clarify beneficio_mensal, data_calculo, tipo, or indice well enough for a caller to populate them confidently.

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 identifies a specific domain and resource: RMC/RCC reserva de margem consignável de cartão (INSS, códigos 217/268), and names what the calculation covers: limites de 5% e restituição corrigida dos descontos. This distinguishes it from most calculo_* siblings, but it lacks an explicit verb like 'calculates', so it is clear yet not fully explicit.

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: the tool is for INSS RMC/RCC margin calculations where a revolving card was sold as consignado and never amortizes. However, there is no explicit when/when-not guidance or comparison with closely related siblings such as calculo_restituicao_inss, so the agent must infer the selection 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?

The annotations already indicate a safe, read-only, idempotent operation. The description adds meaningful behavioral detail by revealing the coefficient rule (60% + 2% per year above 20 years for men / 15 for women) and the floor/cap application. There is no contradiction with 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 a single dense, front-loaded sentence with no filler. It packs the formula, the sex-specific thresholds, and the floor/cap behavior into a compact definition, which is appropriate for a specialist calculation tool.

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 moderate complexity and the absence of an output schema, the description covers the calculation logic, required inputs, and the floor/cap constraints well. It leaves minor ambiguity around whether optional teto_inss and salario_minimo use defaults when omitted, but this does not prevent an agent from invoking the tool with the required parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It effectively maps media_salarios, tempo_contribuicao_anos, sexo, salario_minimo, and teto_inss to the formula, including the sex-specific threshold. It does not name the parameters explicitly or explain defaults, but the formula provides substantial semantic 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 identifies the resource (RMI — Renda Mensal Inicial) and states the exact calculation formula: average contribution salary times a coefficient, with floor and ceiling. It does not explicitly use a verb like 'calculates' or differentiate from sibling tools by name, so it falls just short of a 5.

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 post-reform RMI, especially by specifying 'pós-reforma EC 103/2019'. However, it provides no explicit guidance on when to use this tool versus related siblings such as calculo_pensao or calculo_rmc_rcc, and no exclusions are stated.

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, idempotentHint=true, and destructiveHint=false. The description adds the useful context that the value is dynamic and comes from IPEADATA, but it does not disclose behavior for years without data, update cadence, or response shape. With annotations covering safety, a mid-range score is appropriate.

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

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

The description is a single, dense sentence with no filler. It front-loads the core resource and source, then gives the legal context. Every phrase earns its place.

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

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

For a simple read-only lookup, the description gives the essential purpose, source, and use cases. However, there is no output schema and the optional ano parameter is not explained in terms of default behavior, so an agent cannot be fully certain how to invoke it without additional inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one parameter, ano, as a number with 0% description coverage. The phrase 'de um ano' in the description maps that parameter to a year, and the parameter name and type make the intent fairly clear. However, the description does not explain whether the year is required, what happens if omitted, or what range of years is accepted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing the current national minimum wage for a year, sourced from IPEADATA, and ties it to specific legal uses (dia-multa, pensão, mínimo existencial). It lacks an explicit verb and does not explicitly distinguish itself from sibling tools, so it stops short of a 5.

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 concrete application contexts: dosimetria, pensão por percentual do salário mínimo, and mínimo existencial. This tells an agent when the tool is relevant, but it does not state when not to use it or point to an alternative sibling 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?

As anotações já declaram readOnlyHint=true, idempotentHint=true e destructiveHint=false, cobrindo a segurança da operação. A descrição acrescenta contexto útil: a base legal, o valor padrão parametrizável do mínimo existencial (R$600) e os resultados esperados, incluindo capacidade de pagamento em plano de até 5 anos.

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

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

A descrição é uma frase única, compacta e organizada, começando pelo domínio jurídico e seguindo com os indicadores calculados. Não há redundância nem conteúdo irrelevante.

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?

Não há output schema e a operação calcula múltiplos valores, mas a descrição não informa o formato de retorno, nem os requisitos das entradas obrigatórias ou o comportamento de prazo_meses. Para uma ferramenta de cálculo jurídico com 4 parâmetros, faltam orientações essenciais para uso autônomo.

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?

A cobertura do schema é 0%, então a descrição deveria compensar explicando os parâmetros. Ela apenas informa que o mínimo existencial é parametrizável com padrão de R$600, deixando sem documentação renda_liquida, dividas e prazo_meses. Isso é insuficiente para montar corretamente a chamada.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

A descrição identifica claramente o domínio e os indicadores calculados: percentual da renda comprometida, mínimo existencial, renda disponível e capacidade de pagamento, com base na Lei 14.181/2021. Isso distingue a ferramenta dos demais cálculos jurídicos do conjunto, embora o verbo 'calcular' fique implícito.

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?

O uso fica implícito pela menção a superendividamento e à lei aplicável, mas não há orientação explícita sobre quando usar esta ferramenta em vez de alternativas como calculo_revisional ou calculo_renda. Também não há exclusões ou condições de uso descritas.

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 readOnly, idempotent, and non-destructive hints, so the safety profile is covered. The description adds substantial behavioral context well beyond annotations: it explains how overlapping vínculos are counted only once, how special activity is converted to common time with specific EC 103/2019 factors only up to 13/11/2019, and what the return values are. 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 two dense sentences with no filler. The core purpose and key algorithmic nuances are front-loaded, and every clause adds information about input handling or output. It is an efficient, well-structured description that an agent can parse quickly.

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

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

The description explains the main algorithm and return semantics ('tempo total e se atinge o tempo antigo'), which is essential since there is no output schema. It does not specify the exact return format, date formats for inicio/fim, or how missing tipo is treated, but these are minor gaps for an agent selecting and invoking the tool. Given the calculation's complexity and the lack of an output schema, the description is close to complete but leaves a few details to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does: 'soma os vínculos' clarifies the vinculos parameter, 'conta concomitância uma vez' defines how overlapping periods are treated, and '35H/30M' implies sexo determines the threshold. However, it doesn't explicitly explain the sexo H/M values or the exact structure of inicio/fim/tipo beyond the schema, so it is strong but not fully comprehensive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb-resource pair: summing CNIS contribution links and converting special activity to common time. It clearly distinguishes the tool from siblings like calculo_rmi or calculo_pensao because it targets contribution-time computation for old-age benefit eligibility. The inclusion of formula behaviors (concomitance counted once, EC 103/2019 factors) makes the purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to compute total contribution time and check whether it reaches the old-age threshold, but it never explicitly says when to choose this tool over a sibling. There is no 'use X instead' guidance or exclusion criteria. The context is clear enough for a rough decision, but explicit routing is absent.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context beyond those annotations: the 2026 INSS/IRRF tables, the Lei 12.506/2011 notice rules, the 40%/20% FGTS penalty variants, and the exemption of indemnity amounts. It does not discuss edge cases or rounding, but the annotation coverage lowers that burden.

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

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

The description is a single dense sentence that front-loads the tool's identity and then compactly lists all covered components with useful parentheticals such as the law citation and the 2026 tables. There is no fluff, repetition, or extraneous marketing language.

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 9 parameters, no output schema, and zero schema-level property descriptions, the definition leaves significant invocation gaps: date formats, currency units, how motivo and aviso alter the calculation, and what the returned result contains. The description is sufficient for tool discovery but not fully adequate for reliable autonomous invocation without additional documentation.

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 schema description coverage is 0%, so the description bears the full burden of explaining 9 parameters. While salario, admissao, and demissao are somewhat self-evident, the description does not map optional parameters like projetar_aviso, saldo_fgts, dependentes, motivo, or aviso to specific calculation components, nor does it specify value formats. It describes outputs and legal concepts rather than parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Verbas rescisórias / liquidação trabalhista (CLT)', which clearly identifies the specific domain of labor termination pay calculation. It then enumerates the covered components — salary balance, prior notice, proportional 13th, proportional vacations + 1/3, FGTS penalties, and INSS/IRRF discounts — making the tool's purpose unmistakable and distinguishing it from sibling calculators like calculo_fgts or calculo_tempo_contribuicao.

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 context for when the tool applies (CLT termination/liquidation), which makes its intended use inferable. However, it does not explicitly name alternatives or state when not to use it, such as 'use calculo_fgts for standalone FGTS calculations', so some routing burden is left to the 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds concrete behavioral detail about response states, including authenticated:true with empty pending[] and connect_url when credentials are missing, which goes 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?

Two tight sentences, with the core purpose ('Returns connection status and URLs') front-loaded and the two key response states succinctly described. No filler and no repetition of information already present in the annotations or schema.

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 no-parameter, read-only status tool, the description covers the primary response scenarios. However, it leaves some ambiguity about intermediate states (e.g., partial provider connection) and the exact structure of the URLs, which is a minor gap given the absence of an 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?

The input schema has zero parameters, so there is no parameter semantics for the description to explain. Baseline for zero parameters is 4, and the description correctly avoids any parameter discussion because parameters do not exist.

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 exact action ('Returns connection status and URLs') and clarifies that 'connect' is a read-only status check rather than an action that initiates a connection. The conditional response states distinguish it from sibling tools like authenticate, which presumably performs authentication.

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 conditional context ('When all providers are connected... When credentials are missing...') which implies it is for checking connection state, but it never explicitly says when to use connect over authenticate or any other sibling. No exclusions or alternative routing are given.

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

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

The description discloses critical non-obvious behavior far beyond the annotations: invoke runs tools even when not installed and without bloating the tool list, missing credentials yield a connect link, empty wallets yield a checkout/top-up link with retry semantics, and install/uninstall/subscribe/cancel require privileged roles. It adds rich context that the generic annotations (readOnlyHint=false, destructiveHint=false) cannot convey.

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 very long, dense single paragraph with no paragraph breaks or bullet structure, making it hard to scan despite every sentence carrying real content. It is appropriately sized for the tool's complexity, but the wall-of-text format and the appended prompt-library section hurt readability.

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

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

For a tool with 14 actions, 23 parameters, no output schema, and no schema descriptions, the description covers the main flows, auth/permission requirements, billing edge cases, retry behavior, installed-state flags, and the prompt library. Gaps remain — the 'resume' action is never mentioned, return-value behavior per action is unspecified, and several parameters lack context — but for this scope it is remarkably 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 0% schema description coverage and 23 parameters, the description carries the full burden and compensates well for the core flow: it explains how mcp_id, tool_id, action, and arguments relate to search/describe/invoke, and describes prompt-related parameters (prompt_slug, prompt_vars, prompt_body) in the prompt-library section. However, several parameters (limit, query, immediate, tier_slug, cancel_reason, conversation, report_context, prompt_targets, etc.) remain unexplained, so compensation is strong but incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource — the mcp.ai marketplace — and names its distinct verbs: discover (search/describe), run (invoke), make permanent (install), manage billing (subscribe/cancel), and handle prompts. It clearly differentiates this tool from siblings by defining its scope as the in-platform catalog and runner for MCPs. No ambiguity about what this tool does.

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 an explicit core flow (search → describe → invoke), contrasts install vs invoke with a clear preference ('Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'), and routes sub-actions (list_tools, report_bug, request_mcp, subscribe/cancel) with their purposes. It even states who may perform writes (owner/admin). This is exemplary routing 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 cover the read-only/destructive/idempotent safety profile, and the description adds the useful detail that the conversation should be included for reproduction. However, it does not disclose what happens after reporting, such as whether a ticket is created or whether repeated calls produce duplicate reports.

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, each earning its place: the first states purpose clearly and the second gives a concrete invocation hint. There is no redundant or filler 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?

For a tool with three parameters, no output schema, and low schema coverage, the description is too sparse. It does not clarify the meaning of all parameters, the response format, or the actual side effect of submitting a report, leaving important gaps for an agent to guess about.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only explains the 'conversation' parameter. The required 'message' parameter and the 'context' parameter are not directly described, and the description calls conversation an 'array' while the schema declares it as type 'string', which could mislead an agent.

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 a specific verb ('report' / 'send') and the resource it acts on ('bug', 'missing feature', 'feedback'). It is distinct from the sibling calculator tools and leaves no ambiguity about what action the tool performs.

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 clear usage context: use this tool when the user wants to report a bug, request a missing feature, or send feedback. It does not explicitly name alternatives or exclusions, but none of the sibling tools are relevant alternatives for these intents.

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 cover readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds no behavioral context beyond 'current', which is acceptable for a simple version-query tool but does not go 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?

A single, front-loaded sentence with no filler. Every word contributes meaning, and the size is appropriate for a tool with zero parameters.

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

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

For a zero-parameter, read-only, idempotent tool with no output schema, the description is fully adequate. An agent can select and invoke it correctly with only this description plus 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?

There are zero parameters and empty schema, so the baseline is 4. The description correctly implies that no input is required; no additional parameter semantics are needed.

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 states a specific verb ('Show') and resource ('current MCP platform and adapter versions'). This is clearly distinct from all sibling tools, which are calculation and authentication tools, so an agent can easily tell this is the version-info tool.

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?

There are no alternatives among siblings that do anything similar, so no exclusion guidance is needed. The description's clear scope ('current MCP platform and adapter versions') gives sufficient context for when to invoke it, though it does not explicitly state 'use when...'.

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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context by enumerating exactly what information is returned: installed MCPs, connection status, connected accounts, and catalog tool counts.

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

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

A single, well-structured sentence that front-loads the verb and resource, then lists the returned information in a clear list. Every word earns its place.

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

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

For a parameterless, read-only, idempotent introspection tool, the description is fully adequate. It states the return contents, annotations cover safety, and no output schema is required.

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 tool has zero parameters, so the baseline is 4. The description correctly focuses on the output content rather than parameters, and no parameter documentation is needed.

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 uses a specific verb ('Returns') and clearly identifies the resource ('current toolkit state') with concrete details about what that state includes. This differentiates it from sibling tools by being introspection-focused rather than computation- or auth-related.

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 inspecting toolkit state, which is enough to infer when to use it. However, it does not explicitly state when not to use it or mention any alternative sibling tool for related needs, leaving some routing to the agent.

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