Investigação Cadastral

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

Annotations already cover safety (idempotent, non-destructive). The description adds valuable behavioral context: it explains that calling with no args returns a link, that a token provides session-only login, and that config-based tokens create non-expiring connections. This goes beyond annotations without contradicting 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?

The description is concise, using two sentences that front-load the purpose and then expand on usage details. While the second sentence is long, it packs necessary information efficiently without redundancy. It earns a high score for structure but loses a point for slightly informal tone and density.

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 (one optional parameter, no output schema), the description covers all essential context: how to authenticate, the two modes (config vs. session), and the behavior of calling with no args. It does not explicitly state what happens on success (e.g., a confirmation message), but this is low-risk for an authentication tool and the description is sufficient for correct invocation.

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

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

With 0% schema coverage, the description fully compensates by explaining the token parameter: it is a JWT to paste for session-only login, and the call pattern is explicitly shown ({ token: "<jwt>" }). The description also clarifies when to omit it (to get the link), giving complete 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 clearly identifies the tool as an authentication mechanism for MCP.AI IDE agents, specifying the action (log in) and the resource (access token). It distinguishes itself from sibling investigation tools by focusing solely on authentication, and the informal but precise language leaves no ambiguity about its purpose.

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 usage guidance: it recommends configuring a header for permanent connections and explains exactly when to call with a token (after user pastes) versus no args (to get the link). It also clarifies the session-only versus permanent distinction, giving the agent clear decision points for invocation.

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, destructiveHint: false, so safety is covered. The description adds valuable context about the two distinct output scenarios (authenticated vs missing credentials), which goes beyond what annotations provide.

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 concise sentences that are front-loaded with the primary purpose. The second sentence adds conditional detail without unnecessary words. 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 simplicity (no params, no output schema) and strong annotation coverage, the description adequately covers the main use cases. Minor gaps like defining 'pending' or the exact structure of URLs are acceptable for this context, but it could be slightly more explicit.

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, and the schema is empty with 100% coverage. Per the calibration baseline, a 0-param tool scores 4, and there are no parameter meanings to add since none 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?

Clearly states it returns connection status and URLs, and provides specific conditions for authenticated:true and empty pending[] vs connect_url when credentials are missing. This is a specific verb+resource statement that easily distinguishes it from sibling investigation 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 checking connection status, but does not explicitly contrast with alternatives like 'authenticate' or state when not to use it. It gives some context about output conditions but lacks explicit when-to-use guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 'rede' (network) behavior and AML context, but it does not disclose output format, depth, or whether results are filtered or complete. 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 short sentence that is front-loaded with the key resource and purpose. Every word adds meaning and there is no redundancy 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 two-parameter read-only tool, the description is enough to understand the general intent but not enough to confidently invoke it: the 'completo' parameter behavior and the expected output are undocumented, and there is no output schema to compensate. It is minimally viable but has clear gaps.

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

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

The schema has 0% description coverage, and the description only clarifies the CPF parameter through 'por CPF'. The 'completo' boolean is entirely unexplained, leaving a critical parameter undocumented.

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 ('rede de vínculos societários'), the input scope ('por CPF'), and the purpose ('prevenção à lavagem de dinheiro'), making the tool's function clear. However, it lacks an explicit action verb such as 'retorna' or 'consulta' and does not directly contrast with the sibling investigacao_vinculos_societarios.

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

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

No guidance is given about when to use this tool versus alternatives such as investigacao_vinculos_societarios or investigacao_beneficiario_final. The AML context and CPF parameter imply a use case, but no exclusions or comparisons 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the description does not need to repeat those. However, the description adds minimal behavioral context: it indicates the subject type (company or person) and UBO concept, but does not disclose any details about the return format, privacy, or data completeness. It neither contradicts nor richly supplements 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, short sentence, which is concise and front-loaded. It contains no fluff. However, it is almost too brief, lacking key details, but for what it does include, it 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?

Given there is no output schema and the tool involves 3 parameters with no descriptions, the description is incomplete. It does not mention required inputs (although none are required), how the 'completo' flag affects the response, or any edge cases. The tool is likely part of a larger investigation suite, but without more guidance, agents may misuse 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?

With 0% schema description coverage and no parameter descriptions in the schema itself, the description carries the burden of explaining parameters. It does not explain what CPF, CNPJ, or completo mean or how they are used. The parameter names are self-explanatory to some extent, but the description adds no semantics beyond the schema names, which is insufficient.

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 'Beneficiário final (UBO) de uma empresa ou pessoa' expresses the resource (UBO) and that it relates to a company or person, but it does not state the action (e.g., 'consulta', 'obter', 'investiga'). It is clear in conjunction with the name, but does not distinguish from sibling investigation tools, many of which relate to people or companies.

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

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

The description implies this tool is for obtaining UBO information about a company or person, but it does not explicitly state when to use it over sibling tools like investigacao_pessoa_fisica or investigacao_pessoa_juridica, nor does it provide any exclusion criteria. It is sufficient for a basic understanding 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds the scope (benefits per CPF) but doesn't disclose details like data sources, update frequency, or whether the 'completo' parameter affects response size or latency.

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 sentence that front-loads the purpose. It is efficient, though it could add a brief note on the 'completo' parameter without becoming verbose.

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 and 0% parameter coverage, the description is insufficient. It doesn't explain what data is returned, how the 'completo' flag alters results, or any limitations. For a tool with two parameters and no structured output, more detail is needed.

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

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

Schema description coverage is 0%, so the description must compensate. It mentions the CPF parameter implicitly ('recebidos por um CPF') but does not explain the 'completo' boolean parameter at all. The description adds minimal meaning beyond the schema's 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 clearly states the tool retrieves social benefits received by a CPF, listing examples (Bolsa Família, BPC). It distinguishes from siblings by specifying the resource (social benefits) and the key (CPF), though it doesn't explicitly contrast with other investigacao_* 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 querying social benefits by CPF, but provides no explicit guidance on when to use this tool versus alternatives (e.g., investigacao_renda, investigacao_pis). No exclusions or prerequisites 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the read-only safety profile is covered. The description adds no additional behavioral context such as return format, data completeness, or system behavior, but it also does not contradict 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 extremely concise and front-loaded, with no filler words or redundant information. It could afford a bit more structure to explain the 'completo' parameter, but as a short lookup phrase it is appropriately 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?

With no output schema and 0% schema coverage, the description leaves important gaps: the meaning of 'completo', expected CPF formatting, and what data fields will be returned. It is minimally sufficient for identifying the domain but not complete enough for confident 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 description coverage is 0%, so the description must carry parameter meaning. It mentions 'CPF' as the lookup key but does not explain the 'completo' boolean parameter at all, leaving a significant ambiguity for correct invocation.

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 (CNH data) and the lookup key (CPF), and the 'CNH' term distinguishes it from sibling investigation tools. It lacks an explicit verb like 'consult' or 'retrieve,' but the intent is 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?

No guidance is provided about when to use this tool versus alternatives such as investigacao_pessoa_fisica or investigacao_beneficios_sociais. The 'por CPF' phrase implies the input key, but there is no explicit when-to-use, exclusions, or 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 and idempotentHint=true, so the agent knows it's a safe read operation. The description adds no additional behavioral details (e.g., return format, required combos, auth) beyond the purpose. It does not contradict annotations, so baseline 3 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, front-loaded sentence that conveys the core purpose without fluff. It earns its place, though it could include more detail without becoming verbose.

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 3 parameters, no output schema, and 0% schema coverage, the description must compensate by explaining parameter usage. It fails to clarify the EMAIL/CELULAR combo logic or the 'completo' boolean, leaving the agent guessing about invocation. Return values are also unaddressed.

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 adds zero information about the three parameters (EMAIL, CELULAR, completo) — no types, meanings, or relationships. The agent is left guessing what 'completo' means or whether both EMAIL and CELULAR should be provided.

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: discovering a person behind a phone and/or email (reverse enrichment). The verb 'descobre' (discovers) plus the explicit resource (phone/email) distinguishes it from sibling tools that target specific domains (e.g., CNH, obito, localizacao).

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 you have a phone/email and want to identify a person, but it does not explicitly state when NOT to use it or mention alternatives. Since siblings are all investigation types, the description's 'e/ou' gives some usage hint but no exclusions or contrasts.

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 that the tool is read-only, idempotent, and non-destructive; the description adds the São Paulo scope without contradicting those hints. It does not add further behavioral context such as required authentication, output behavior, or limitations, so it stays at the baseline given the strong 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 short sentence with no filler and front-loads the core subject and jurisdiction. It is concise, though slightly over-compressed because it omits a verb and details that would improve clarity without much 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 no output schema, no required parameters, and 0% schema description coverage, the description is too thin: it does not state what appears in the returned history, how 'completo' changes the request, or response parameters. The SP scope and tax-id inputs are useful, but the tool is under-specified for reliable 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 description coverage is 0%, so the description carries the burden. It clarifies that CPF or CNPJ are the identifying inputs, but it does not explain their expected format, whether one is mandatory, or what the 'completo' boolean controls. This leaves a meaningful portion of the parameter surface unexplained.

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 ('histórico veicular') and jurisdiction ('SP'), and the 'por CPF ou CNPJ' qualifier helps distinguish it from sibling tools that search by plate or property. However, it lacks a verb such as 'consultar' or 'retornar', so the action is implicit rather than 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?

The description provides no guidance about when to choose this tool over alternatives like investigacao_propriedade_veicular or investigacao_veiculo_placa, nor any exclusions. 'Por CPF ou CNPJ' implies an input requirement but not a usage scenario or selection criterion.

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 and destructiveHint=false, so the safety profile is covered. The description adds little beyond stating the action; it does not mention limitations, potential failures, or any procedural details, but for a simple lookup, this is acceptable given the annotation 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 concise sentence, which is efficient, but it lacks structure (no breakdown of inputs vs outputs) and does not front-load key usage hints. It is not verbose, but the brevity comes at the cost of 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 no output schema and no parameter descriptions, the tool description is insufficient for an agent to know what inputs to provide or what the result will look like. The description only states the high-level purpose, leaving the agent to guess how to invoke the tool 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?

The input schema has no descriptions for CPF, DOB, NAME, SURNAME, and the description only mentions output fields (name, address, phone, email) without linking them to inputs. This offers minimal guidance on how parameters are used or which are required, failing to compensate for the schema's lack of detail.

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: locating a person via name, address, phone, or email. It uses a specific verb ('Localização') and resource ('pessoa'), and the listed fields help define the scope. However, it does not explicitly distinguish itself from sibling investigation tools, though the unique focus on contact details sets it apart implicitly.

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 conveys the context of use (locating a person's details) without ambiguity. It does not explicitly mention when not to use this tool or compare it to alternatives like 'investigacao_pessoa_juridica' or 'investigacao_propriedade_veicular', but the clear purpose makes the distinction obvious.

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 já declaram readOnlyHint=true, idempotentHint=true, destructiveHint=false, então o perfil de segurança é coberto. A descrição não adiciona nada além disso (ex: se requer autenticação, formato da resposta, limitações de dados), mas não contradiz as 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?

Uma frase curta e direta, sem excesso. Porém, é tão minimalista que pode ser mais subespecificação do que concisão, mas ainda assim é estruturalmente clara.

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

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

Para um tool com 2 parâmetros (um booleano ambíguo) e sem schema rico, a descrição é insuficiente. Não informa o que o parâmetro 'completo' faz, nem o formato de retorno ou possíveis restrições. Annotations ajudam na segurança, mas não na usabilidade.

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 descrição menciona o parâmetro CPF implicitamente, mas não explica o significado do parâmetro 'completo' (booleano) que não é auto-explicativo. Com 0% de cobertura do schema, a descrição deveria compensar e não o faz adequadamente.

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 'Verificação de óbito por CPF.' indica claramente o verbo (verificar) e o recurso (óbito via CPF), distinguindo-se dos demais tools de investigação pelo domínio específico. Embora não detalhe escopo, o propósito é direto e suficiente.

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?

Não há orientação sobre quando usar este tool em relação aos alternativos, nem exclusions. A presença de siblings similares (ex: investigacao_pessoa_fisica) sem qualquer menção a critérios de escolha deixa o agente sem guia contextual.

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 the operation read-only, idempotent, and non-destructive, so the description does not need to restate that. It adds some context about the returned subject matter (shareholders and linked companies), but it does not disclose behavior such as authentication needs, rate limits, or the effect of the optional 'completo' flag.

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, front-loaded sentence with no filler. It conveys the core idea efficiently: QSA, corporate holdings, shareholders, and linked companies for a CNPJ.

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 enough context to understand the tool's purpose, but it still leaves invocation details ambiguous, especially the meaning of 'completo'. Since there is no output schema, some information about what the tool returns would also help.

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 only mentions that CNPJ is the target entity and says nothing about the 'completo' boolean parameter, its default value, or what changes when true.

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 communicates a specific resource (CNPJ) and a specific data scope (QSA, shareholders, and linked companies), so an agent can tell what this tool returns. It lacks an explicit verb and does not clearly differentiate it from the closely related sibling investigacao_vinculos_societarios, 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?

Usage is only implied: this is for investigating corporate ownership/participations for a CNPJ. There is no explicit guidance about when to use this over sibling tools, no exclusions, and no mention of required conditions such as needing a valid CNPJ.

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 clear. The description adds no behavioral details beyond what annotations provide, such as data freshness, privacy restrictions, or output formatting. It meets the baseline but does not exceed it.

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, a single sentence that is front-loaded and free of fluff. It efficiently lists the key data points. However, it could be improved by including usage context on the parameters, but the conciseness itself is well executed.

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 only 2 parameters and no output schema. The description provides a good overview of the returned data, but it omits critical usage details such as how to specify the CPF (format), the effect of 'completo', and any prerequisites like authentication. Given the moderate complexity, the description is adequate but not fully 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 description coverage is 0%, so the description must compensate for the parameters. It implies the main parameter is the CPF, and 'completo' likely controls the comprehensiveness of the output telegraphically. However, the description does not explain the difference between a complete and incomplete query, nor does it clarify what the boolean 'completo' changes. It provides partial compensation but leaves key parameter semantics unclear.

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

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

The description clearly states the purpose: returning complete registration data for a CPF, listing specific data fields (name, contact, address, income, salary range). It distinguishes itself from sibling tools like investigacao_renda and investigacao_pessoa_juridica by focusing on individual taxpayer registration data.

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

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

The description does not provide any guidance on when to use this tool versus alternatives. It does not mention when to prefer this over investigacao_renda or investigacao_pessoa_juridica, nor does it indicate prerequisites like authentication or needed input format.

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, so the agent knows this is a safe, read-only operation. The description adds no extra behavioral details (e.g., whether authentication is required, rate limits, or what 'complete' data includes). Given the annotations cover safety, the description meets the baseline but doesn't add beyond that. A score of 3 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, short sentence that front-loads the core purpose. It is concise and to the point, 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?

For a simple lookup tool with 2 parameters and no output schema, the description is minimal. It does not explain the meaning of the 'completo' flag, the expected format of the CNPJ (e.g., with or without punctuation), or what kind of data will be returned. Given the complexity of a CNPJ lookup (corporate registration data can include a lot), the description is incomplete for an agent to correctly invoke the tool and interpret 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 0%. The description says 'complete registration data' but does not explain what the parameters 'CNPJ' or 'completo' mean. The boolean 'completo' is particularly ambiguous—does it request full data vs. summary? No guidance is provided. With no parameter descriptions in the schema and no compensation in the description, this is severely lacking.

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 'Dados cadastrais completos de um CNPJ' clearly states the tool provides complete registration data for a CNPJ (Brazilian company ID). This distinguishes it from sibling tools like investigacao_pessoa_fisica (individual) and other specific investigation tools, though it doesn't explicitly contrast them. The verb is implicit ('provides') but the resource and scope are clear.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention any context, prerequisites, or exclusions. An agent must infer from the name alone that it's for legal entity data, and there's no indication when to choose this over sibling tools like investigacao_vinculos_societarios or investigacao_beneficiario_final.

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, destructiveHint=false. The description adds no behavioral details (e.g., what data is returned, whether a full record or only PIS, any side effects). It doesn't contradict annotations, but contributes nothing extra.

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 short phrase, which is concise but so under-specified that it fails to convey essential information. It's not a run-on, but it's too minimal to be useful; it lacks structure and front-loading of key 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?

Given the tool has two parameters (one boolean) and no output schema, the description is severely incomplete. It doesn't explain the 'completo' parameter, the output format, or any operational details. Compared to sibling investigation tools, this description is far too sparse.

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

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

Schema has CPF (string) and completo (boolean) with zero description coverage. The description only mentions CPF implicitly via 'CPF' and says nothing about 'completo' (whether to return full details or just the PIS). No parameter semantics are provided.

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 'PIS vinculado a um CPF' identifies the resource (PIS) and implies a query on a CPF, but it lacks an explicit verb or action. It distinguishes from siblings by name alone, not by describing the specific function clearly. It's not a tautology, but it's vague.

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

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

No guidance on when to use this tool versus the many other investigacao_* siblings. It doesn't mention prerequisites, typical use cases, or exclusions. The description gives no context beyond the resource.

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 idempotentHint=true, covering safety. The description adds the specific resource (PRF infractions) but provides no additional behavioral details such as data freshness, limitations, or authentication requirements. With annotations carrying the safety profile, this is acceptable but minimal.

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 sentence that front-loads the core purpose. It is efficient, with zero wasted words, and effectively communicates the tool's primary function.

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 4 parameters, no output schema, and no parameter descriptions, the single-line description is insufficient. It doesn't explain return data, parameter options, or usage context, making it incomplete 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 has 4 parameters with 0% description coverage. The description only mentions plate and RENAVAM but ignores TIPO and 'completo', leaving their semantics unclear. It fails to compensate for the lack of schema descriptions, so the agent lacks critical parameter understanding.

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

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

The description clearly states the tool retrieves PRF infractions by plate and RENAVAM, distinguishing it from sibling investigation tools focused on other domains like CNH or vehicle history. 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?

No guidance is provided on when to use this tool versus other investigation tools, such as investigacao_cnh or investigacao_veiculo_placa. It simply states the function without context, prerequisites, or exclusions, leaving the agent to infer usage.

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 with readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate those. The description adds some context about the query scope (by CPF/CNPJ, fleet), but it does not disclose additional behavioral traits such as result limitations, response shape, or any constraints on the input combination.

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 phrase with no filler or repetition. It front-loads the main subject and lookup key, but the lack of a verb makes it slightly elliptical; despite that, it is appropriately sized for a simple lookup 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?

This is a simple lookup tool with rich annotations, but the description leaves important usage details unaddressed: the role of 'completo', how CPF and CNPJ interact, and when to prefer this tool over related vehicle investigation tools. With no output schema present, the description needed to carry more weight than it does.

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 that CPF/CNPJ are identifiers for the search. The 'completo' boolean parameter is completely unexplained, and there is no guidance on whether CPF or CNPJ is required, whether they are mutually exclusive, or what 'completo' changes about the results.

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

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

The description clearly states that the tool returns vehicles registered under a person or company, searched by CPF/CNPJ. It also implies a fleet-level scope, which helps distinguish it from sibling tools like investigacao_veiculo_placa. However, it uses a noun phrase rather than a specific verb such as 'list' or 'search', so it stops short of a fully explicit purpose 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?

No guidance is provided about when to use this tool versus alternatives such as investigacao_veiculo_placa or investigacao_historico_veicular. There is no mention of when a CPF/CNPJ-based property lookup is appropriate, nor any 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?

A descrição menciona 'renda estimada', indicando que o valor não é exato, o que é uma informação comportamental relevante e não coberta pelas anotações (readOnlyHint, idempotentHint, etc.). No entanto, não há detalhes sobre como a estimativa é calculada, possíveis variações, ou o que acontece se o CPF não é encontrado. As anotações indicam que é uma operação segura e de leitura, então a falta de detalhes adicionais é aceitável, mas a palavra 'estimada' é o único extra.

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?

O texto é conciso (uma frase) e claro, sem excessos. No entanto, a estrutura é extremamente minimalista, o que pode ser vantajoso em termos de conscisão, mas peca por não fornecer detalhes adicionados. Ah, mas a pontuação alta se deve ao fato de que a descrição é curta e direta, sem palavras desnecessárias. A nota 4 reflete que é eficiente, mas não necessariamente completa.

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

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

A ferramenta tem 2 parâmetros, sem schema de saída, sem anotações detalhadas e sem cobertura de schema. A descrição é mínima e não explica o retorno esperado (embora seja presumível que retorne dados de renda), nem o significado de 'completo'. Dado o contexto, a descrição deveria fornecer mais informações sobre o que o agente pode esperar, como o formato da resposta e possíveis variações. Está subdimensionada para uma ferramenta com esses parâmetros.

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% e a descrição não explica os parâmetros, CPF e completo. A descrição apenas menciona que o CPF é usado, mas não detalha o formato esperado (com ou sem máscara) nem o significado de 'completo' (possivelmente 'retornar todos os dados completos' vs. resumo). Com 2 parâmetros sem nenhuma explicação, é uma lacuna significativa. Como não há outras fontes de informação, a descrição deveria compensar, mas não o faz.

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 'Nível socioeconômico e renda estimada de um CPF' informa claramente que a ferramenta fornece dados socioeconômicos e de renda para um CPF. Apesar de não diferenciar explicitamente dos irmãos, que são todos prefixados com 'investigacao_', o foco em 'renda' e 'nível socioeconômico' é específico o suficiente para distinguir de tópicos como 'veículo', 'CNH' ou 'benefícios'.

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

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

A descrição não fornece orientações sobre quando usar esta ferramenta em detrimento de outras, nem menciona contextos específicos, pré-requisitos ou exclusões. Como há muitas ferramentas irmãs de investigação, seria importante indicar, por exemplo, qual situação leva a consultar renda em vez de outros dados, ou as limitações do dado (ex: se é uma estimativa). Sem isso, o agente tem pouco direcionamento.

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 tool's safety profile is known. The description adds only the TSE source and person scope, but does not disclose output shape, required identifiers, or query-combination behavior.

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, short noun phrase with no filler. It is front-loaded and every word contributes to identifying the tool's core purpose.

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

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

For a 5-parameter tool with no output schema and several similar siblings, this description is too sparse. It provides no query guidance, parameter semantics, or expected result details, leaving the agent to guess how to invoke 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?

The input schema has 5 parameters with 0% description coverage, and the description does not explain CPF, NOME, DATANASCIMENTO, NUMEROTITULOELEITORAL, or completo. The parameter names are self-explanatory, but the description adds virtually no semantic value beyond the schema itself.

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: a person's electoral situation from the TSE. It is specific enough to convey the tool's domain, though it lacks an explicit verb and does not differentiate it from sibling tools like investigacao_titulo_eleitoral.

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 is no guidance about when to use this tool versus alternatives such as investigacao_titulo_eleitoral or investigacao_pessoa_fisica. No exclusions, prerequisites, or alternative tool references 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 indicate read-only, idempotent, and non-destructive behavior, so the description doesn't need to restate those. However, it adds no other behavioral context: it doesn't clarify what exactly is retrieved, whether it returns full details with the 'completo' parameter, or any special handling. The phrase 'Título e local de votação' hints at the output but is not explicit.

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 short phrase, but it is under-specified rather than concise. It lacks essential information about the tool's behavior, parameters, and usage. The brevity does not serve the agent well; it reads more like a tagline than a functional description.

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 6 parameters, no output schema, and no description of return values or behavior, the tool is severely under-documented. The description offers only a vague subject reference and fails to provide any guidance for basic usage, leaving the agent to infer everything from the 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 0%, so the description must compensate by explaining the parameters. It provides no explanation for any of the 6 parameters, nor does it mention that DATANASCIMENTO and NOMEMAE are required. The description adds no meaning beyond the schema field names, which are already self-explanatory.

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

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

The description 'Título e local de votação (TSE)' is a noun phrase that indicates the subject (voter registration title and voting location) but fails to state an action. It barely distinguishes from siblings like 'investigacao_situacao_eleitoral' which also deals with electoral matters. It is not a tautology but is too vague to convey what the 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?

No usage guidance is provided. The description does not indicate when to use this tool, what prerequisites exist, or when to prefer an alternative sibling like 'investigacao_situacao_eleitoral'. No context 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that no RENAVAM is required, which is a usage constraint rather than a behavior. It does not mention output format, pagination, or any side effects, but given the annotations cover the main safety aspects, this is adequate. It adds a bit of context (what data is returned) but falls short of describing behaviors like response structure.

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 sentence that conveys the core purpose and a key differentiator. There is zero fluff, and it is immediately understandable. It front-loads the primary action and condition effectively.

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 simple (2 params, no output schema, no nested objects), the description is mostly complete: it states the resource (vehicle by plate) and the outcome (data and debts). However, the unexplained 'completo' parameter creates a hole in completeness. Also, it doesn't specify any prerequisites (e.g., plate format) or return details, though for a simple query this might be acceptable. The tool belongs to a set of investigation tools, and the description differentiates it via the RENAVAM requirement, but it doesn't provide enough for a user to fully know the tool's 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 full burden for explaining parameters. It implicitly clarifies PLACA (plate) via 'pela placa', but the 'completo' boolean parameter is completely unexplained. The user has no idea what 'completo' controls (e.g., include all details or just summary). This is a significant gap for one of two parameters.

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

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

The description clearly states what the tool does: it returns data and debts of a vehicle from its plate. It also differentiates from siblings by noting 'não exige RENAVAM', which indicates it works without that identifier. However, 'dados e débitos' is somewhat generic, and the scope of 'data' is not specified, so it's not a perfect 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 usage when the user only has the plate and no RENAVAM, but it does not explicitly name alternative tools or state when not to use this tool. Siblings like investigacao_historico_veicular or investigacao_propriedade_veicular exist, but no comparison is given. Thus, usage guidance is implied but not explicit.

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, which cover safety. The description adds no behavioral detail beyond that—no mention of auth requirements, return format, pagination, or the effect of the 'completo' flag. It is not contradictory but contributes little.

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 extremely short, but this is under-specification rather than concise guidance. A three-word noun phrase does not provide enough structure or actionable content for an agent to confidently select and invoke 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 tool with two optional parameters, no output schema, and many sibling investigation tools, the description is inadequate. It omits what the result looks like, how 'completo' changes the response, and which scenarios call for this tool over related ones.

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 for explaining CNPJ and completo, but it says nothing about either parameter. The parameter names are self-explanatory only in isolation; the tool description provides no additional 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 'Vínculos empregatícios' restates the tool name 'investigacao_vinculo_empregaticio' without a verb or explicit operation, making it a tautology. It does not distinguish this from sibling tools like investigacao_vinculos_societarios or indicate what the investigation returns.

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

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

No guidance is provided about when to use this tool, what inputs trigger different behaviors, or how it relates to alternatives such as investigacao_pessoa_juridica or investigacao_vinculos_societarios. The optional CNPJ and completo parameters are not tied to use cases.

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, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds minimal behavioral context beyond that, such as the scope of data (societary links). However, it doesn't disclose details like whether results are limited to direct links or include indirect relationships, schema coverage is absent, and no output schema exists. It doesn't contradict the annotations; it just doesn't add much depth.

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 extremely concise: a single sentence that states the purpose. No fluff or redundancy. However, it likely sacrifices necessary detail for brevity, so it's not a 5. It's appropriately structured with the key concept 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?

Given the tool has 3 parameters, no output schema, low schema coverage, and minimal annotations, the description should provide more context. It only states the general purpose, omitting details on parameter usage, outbound data structure, or limitations. Compared to the calibration examples, it's similar to 'update_drive' which scored 2 on completeness because it didn't explain behavior or output for a mutation tool. Here, the tool is a read operation, but still lacks parameter and output context, and the description adds little beyond the name and title.

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 three parameters (CPF, CNPJ, completo) with zero description coverage. The tool description does not explain what these parameters mean or how they interrelate (e.g., whether CPF and CNPJ are mutually exclusive, what 'completo' implies). The description only mentions 'person or company', hinting that CPF relates to a person and CNPJ to a company, but it's not explicit. Since schema coverage is 0%, the description should compensate but doesn't effectively, leaving the agent guessing on parameter usage.

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

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

The description 'Vínculos/relacionamentos societários de uma pessoa ou empresa' clearly states the tool's purpose: it retrieves corporate links/relationships for a person or company. While it names the exact resource (societários links), it doesn't explicitly distinguish it from sibling tools like investigacao_participacoes, which might have overlapping scope, hence a 4 instead of 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 usage by indicating the type of subject (person or company), but it does not provide explicit guidance on when to use this tool versus alternatives like investigacao_participacoes or investigacao_beneficiario_final. It lacks any 'use this instead of X' or conditional 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 (readOnlyHint=false, destructiveHint=false) set a low bar, but the description adds crucial behavioral context: invoke works even without installation, returns connect links for missing credentials, checkout links for empty wallets, and installs/uninstalls are permanent changes requiring owner/admin. It also explains the prompt library and how installed vs. uninstalled status is flagged. No contradictions with annotations; in fact, it enriches 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?

The description is long but appropriately sized for a 14-action tool with 23 parameters. It is front-loaded with the core flow, uses clear structural cues ('KEY:', 'Use install only...', 'Search/describe...'), and every sentence adds value—no filler. It efficiently packs permissions, auth flows, and alternative actions into a well-organized narrative.

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 (14 actions, 23 params, no output schema, minimal annotations), the description covers the major workflows, permission requirements, and the prompt library. However, it omits explicit descriptions of output formats for each action (e.g., what search returns, structure of describe) and leaves some parameters unexplained. It is complete enough for most tasks but has gaps in parameter nuances and return values.

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

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

With 0% schema coverage, the description must compensate. It clearly explains the primary parameters (action, mcp_id, tool_id, arguments, query, limit, prompt_vars, etc.) through the core flow and action descriptions. However, not all 23 parameters are explicitly covered (e.g., conversation, prompt_targets, prompt_category, report_context, etc.), and it does not specify syntax details like arguments being a JSON string. Still, it provides enough semantic grounding for most actions.

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 what the marketplace does: it is the official catalog of MCPs/tools and the way to run them. It clearly enumerates the core flow (search → describe → invoke) and distinguishes itself from sibling investigation tools and report_bug by covering all its actions (search, describe, invoke, install, prompt library, etc.). The verb+resource is specific and comprehensive.

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 each action: prefer invoke for one-off use, use install for permanent additions, list_tools shows what is callable now, and it explains subscribe/cancel, report_bug, request_mcp, and the prompt library actions. It also gives alternatives (e.g., 'prefer invoke for a single/occasional use') and states that writes require workspace owner/admin.

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 idempotentHint=true, readOnlyHint=false, destructiveHint=false, but the description adds the instruction to include a conversation array for reproduction, which is extra context. However, it does not disclose what happens after reporting (e.g., whether data is stored, response format). With annotations present, this is acceptable but not rich.

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

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

The description is one sentence broken into two clear clauses: purpose and a key requirement. No fluff, front-loaded, and every word adds value. Perfectly concise for a simple reporting 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 tool with only 3 parameters, no output schema, and existing annotations, the description covers the core action and a critical input (conversation). It does not explain the response or any follow-up behavior, but given the simplicity and idempotentHint, the description is adequate. Could mention what to do after calling, but not 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?

Schema description coverage is 0%, so the description must compensate. It only explains the 'conversation' parameter ('Include the conversation array'), but does not clarify the meaning of 'message' (the required field) or 'context'. Given 3 parameters and zero schema descriptions, this is incomplete.

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

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

The description clearly states the tool's purpose: 'Report a bug, missing feature, or send feedback.' The verb 'report' and the resource (bug/missing feature/feedback) are specific, and this tool is clearly distinct from all sibling investigation 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 when to use (for reporting bugs/feedback) but does not provide explicit alternatives or exclusions. It hints at usage by mentioning 'Include the conversation array with recent messages for reproduction,' but lacks guidance on when not to use it or contrast with siblings, though siblings are all unrelated investigation 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, so the safety profile is covered. The description adds little behavioral detail beyond 'current', but 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 front-loaded sentence with no filler, repetition, or unnecessary details. Every word adds meaning.

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 version query, the description is complete: it specifies what versions are shown and the annotations cover the non-destructive, idempotent behavior. No output schema is needed for such a simple 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?

The tool has zero parameters and an empty input schema with 100% coverage, so there are no parameter details for the description to explain. Baseline for zero-parameter tools is 4.

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 ('Show') and names the exact resources ('current MCP platform and adapter versions'). This clearly distinguishes it from sibling investigation, authentication, and reporting 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?

There is no explicit when-to-use or alternative guidance, but the purpose strongly implies using this tool whenever version information is needed. No sibling tool competes for this responsibility, so the lack of explicit exclusions is not a major gap.

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 safety is covered. The description adds useful behavioral context by specifying what state is returned, including connection status and account linkage, which goes beyond annotation data.

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 sentence that front-loads the action and resource, then lists the key output components. Every part earns its place with no filler 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?

With zero parameters, no output schema, and a low-complexity state-inspection task, the description is complete. It tells the agent exactly what information will be returned, so no further behavioral or return-format explanation is needed.

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

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

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and it instead focuses on the output content, which is the appropriate semantic information for this tool.

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

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

The description uses a specific verb ('Returns') and names a clear resource ('current toolkit state'), then enumerates exactly what it includes: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from sibling investigation and connection 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 when to use it — when an agent needs an overview of toolkit state — but it does not explicitly state exclusions or alternatives, such as 'use this before connecting' or 'use show_version for version info only.' Context is clear, but no guidance is given.

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