Babá Certa

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

Beyond the readOnly/openWorld/non-destructive annotations, it discloses result ordering (by recent publication, no quality ranking), input rejection rules (no CEP/neighborhood/coordinates, no distance calculation, no location inference), and result semantics (distinguishes an empty list from a technical failure). That is substantial behavioral context the annotations do not carry.

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?

Four short sentences, front-loaded with purpose followed by behavior and exclusions. Every sentence carries distinct, useful information 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?

An output schema exists, so return structure need not be described. The description still covers inputs, ordering, exclusions, and the empty-vs-error distinction, leaving nothing an agent needs to invoke it correctly unstated.

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 value by clarifying that both values come from the person in the conversation and by explicitly rejecting address-level inputs (CEP, bairro, coordinates), which constrains how the two parameters should be populated.

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

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

States a specific verb (consulta) and resource (perfis públicos consentidos) scoped by cidade and UF, so an agent immediately knows this is a search/read operation. The sibling tools are all cost/salary calculators, and this description makes the search function 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?

Gives clear context for use: query public profiles using the city and state provided by the person in the conversation. It also rules out CEP, neighborhood, and coordinates. It does not name an alternative tool, but no sibling is a search alternative, so no exclusion is needed.

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 safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds meaningful behavioral context: it discloses that output includes sources and premises and that the estimate is neither a salary proposal nor a substitute for a collective agreement, which a caller needs to interpret results responsibly.

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 sentences, front-loaded with the core calculation, followed by the conditional usage mode and the disclaimer. Little waste, though the disclaimer sentence could be tighter.

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?

An output schema exists, so return values need not be detailed, and the description still notes it returns fonts and premises. Given the read-only annotations and full schema coverage, the definition supplies enough for an agent to call it correctly.

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

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

Schema coverage is 100% so the baseline is 3, but the description adds semantic value the schema cannot convey: the interaction where omitting salarioBruto while providing UF triggers a reference-based example. This clarifies the otherwise opaque all-optional parameter set.

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

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

States a specific verb (calcula) and resource (custo mensal e anual estimado de contratação doméstica), making the estimation intent clear. It is distinguishable from calcular_salario_liquido by focusing on hiring cost rather than net pay, though it never names that sibling. Clear but without explicit sibling differentiation.

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 a useful usage mode: passing UF without salarioBruto yields an example using the state reference table. However, it gives no guidance on when to prefer this over calcular_salario_liquido or mostrar_busca_e_custo, leaving alternatives 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 declare a safe, non-destructive, closed-world read, so that burden is lifted. The description adds genuine behavioral context: it is a pure estimator that does not presume account data or interpret individual employment links, and it discloses the returned components (INSS, IRRF, transporte, fontes, premissas). It doesn't cover rounding, tax-table year, or precision caveats.

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 tight sentences: purpose first, output contents second, scope exclusion last. No filler, though the return-field sentence partially duplicates the output 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 stateless calculation tool with an output schema present, the description covers purpose, inputs, statelessness, and scope limits, which is enough to call it correctly. Minor missing pieces: the diasUteisMes parameter is neither named nor hinted at, and no note on tax-year assumptions.

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 75% and three of four parameters carry inline descriptions (defaults of 22 workdays and zero transport are documented in the schema). The description restates the main inputs but adds no format, default, or edge-case meaning beyond the schema, so the 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?

States a specific verb (estima) and resource (salário líquido mensal de babá) plus the inputs it consumes, which lets an agent separate it from display siblings like mostrar_salario_liquido. It does not explicitly name a sibling or contrast with calcular_custo_baba, 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?

Usage is implied (compute payroll from supplied gross wage/dependents/transport) and the closing clause rules out account-derived or per-contract interpretation, which hints at scope. However, it never states when to prefer this over calcular_custo_baba or mostrar_salario_liquido, so an agent must infer the routing.

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 safety profile (readOnlyHint true, destructiveHint false, openWorldHint true), and the description is consistent with them. It adds real behavioral context beyond the annotations: it re-runs query and calculation for fresh data, and falls back to the state salary reference when no gross salary is supplied.

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?

Purpose is front-loaded in the first sentence, and the following sentences each carry a distinct fact (prerequisite, refresh behavior, fallback, exclusions). Five short sentences with no filler, though the negative-scope sentence could arguably be tightened.

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

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

The tool has an output schema, so return values need no explanation, and annotations cover safety. The description supplies prerequisites, fallback behavior, and scope boundaries, leaving little an agent needs that is missing.

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 five parameters including defaults. The description reinforces the city/UF requirement and explains the salary fallback, which adds a little beyond the schema, but it still meets the baseline-3 case where the schema does the heavy lifting.

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

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

States two specific verb+resource pairs ('consulta perfis públicos consentidos' and 'calcula custo de contratação') and names the output form ('cartão interativo com detalhes ajustáveis'). It implicitly distinguishes itself from the single-purpose siblings buscar_babas_publicas and calcular_custo_baba by doing both at once, but never says so explicitly.

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?

'Exige cidade e UF informadas pela pessoa na conversa' gives a prerequisite, and 'Não calcula distância nem classifica a qualidade' gives scope exclusions. However, it never states when to pick this combined tool over the individual search/cost siblings, so routing remains inferred.

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, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds real value beyond that by disclosing that the result is an interactive card with adjustable values and that it returns sources and assumptions. It stops short of describing whether values are estimates only or how rounding/versioning of tax tables is handled.

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 short sentences, zero filler: what it does, what it requires, what it accepts, what it returns. The required input is called out early and nothing is repeated.

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 an output schema present, the description needn't explain return values, yet it still flags sources and assumptions, which is helpful for a financial estimate. The remaining gap is sibling disambiguation against calcular_salario_liquido and the default for dependentes, but for a 4-parameter read-only tool this is close to 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 75% and the description enumerates all four inputs by name, explicitly marking salarioBruto as required and grouping the three optional ones (dependentes, vale-transporte, dias úteis). It does not add units or defaults beyond what the schema already states, so it complements rather than extends 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?

States a specific verb+resource ('Calcula e apresenta salário líquido estimado') and adds the delivery form ('cartão interativo com os descontos detalhados e valores ajustáveis'). However, it never distinguishes itself from the near-identically named sibling calcular_salario_liquido, which is the exact confusion an agent must resolve.

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 one prerequisite ('Requer salário bruto informado') and enumerates the optional inputs, which implies the calling context. But it offers no when-to-use/when-not guidance and does not name calcular_salario_liquido as the alternative, so an agent choosing between two net-salary tools gets no routing help.

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