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

No annotations are present, so the description carries the full burden of behavioral disclosure. It mentions the 70 MB limit and that the title must already be launched, but it omits side effects, permission requirements, whether existing files are replaced, and what the tool returns after success or failure.

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

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

The description is two short, front-loaded sentences. The action comes first, followed by the key size limit, with no filler or redundant explanations.

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 3-parameter tool with no output schema, the description provides the core action, file types, a prerequisite, and a hard limit. However, because no annotations exist, success/failure behavior and error conditions are left unstated, making it 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 67%, with 'titulo_id' lacking a description. The description adds meaning by clarifying that the target must be an already-launched title, which helps with 'titulo_id', and it lists allowed file types and the size limit, adding context for 'caminho_arquivo'. It does not go beyond the schema for 'descricao', but the added context keeps this at baseline 3.

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

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

The description states a specific verb and resource: it attaches a file to an already-launched title and enumerates accepted file types (photo of note, PDF, XML). The phrase 'já lançado' distinguishes it from title-creation siblings, giving the agent a clear idea of 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 implicit usage context: the tool is for files attached to already-launched titles, and it includes a 70 MB size limit. However, it does not explicitly say when to use this tool over alternatives such as 'arquivar_nota', nor does it give conditions where the tool should not be used.

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?

With no annotations, the description carries the full burden. It discloses the persistence side effect (writing to config/aprendizado.json) and the learning behavior, but it does not clarify whether existing mappings are overwritten, how duplicates are handled, or what happens on failure.

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

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

The description is two concise sentences with no filler. The core behavior is front-loaded, and the call trigger is given in the second sentence, earning its place.

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

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

Given seven parameters with zero schema descriptionsable, no output schema, and no annotations, this description is not complete enough on its own. An agent would still be uncertain how to populate the parameters and what the tool's exact side effects and return behavior are.

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 needed to compensate, but it only alludes to 'este fornecedor' and 'apropriação' without explaining any of the seven properties. Required fields like centro_custo_id and plano_financeiro_id are not clarified beyond the bare schema definitions.

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

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

The description states a concrete action ('Grava em config/aprendizado.json'), the exact resource affected, and the purpose ('sugerir automaticamente da próxima vez'). It clearly differentiates this tool from the sibling 'sugerir_apropriacao' by describing the learning side of the workflow.

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

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

The description gives an explicit trigger: 'Chame depois de cada título lançado com sucesso.' It provides clear context for when to use the tool, though it does not explicitly state when not to use it or name alternative tools.

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

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

With no annotations, the description carries the burden; it discloses the core relocation behavior, the target path inside the repository, and the local-only guarantee ('Nada sai da máquina'). It does not mention overwrite behavior, what happens to the source file, or failure/return behavior, so it is only partially transparent.

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

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

Two short sentences; the action and destination are front-loaded and the final sentence adds a meaningful privacy constraint with no filler.

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

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

For a mutating file operation with no annotations and no output schema, this is only minimally complete: it supplies the destination and intent, but omits return values, collision/overwrite behavior, and relationship to sibling tools like anexar_arquivo_titulo. An agent could make a plausible call, but important edge-case context 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 coverage is only 25%, but the description compensates somewhat by mapping data_emissao to the AAAA-MM folder and titulo/fornecedor to the filename pattern. However, it never names caminho_arquivo as the source parameter or clarifies how titulo_id maps to the '<titulo>' component, leaving required parameter semantics partly underspecified.

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 ('Move') and a specific resource ('foto/arquivo da nota já lançada') plus a full destination path. The phrase 'já lançada' and the archive folder make it distinct from sibling operations like anexar_arquivo_titulo or criar_titulo even without naming them.

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 clearly states this is for notes that have already been posted ('já lançada') and frames the move as preventing duplicate posting ('para não lançar duas vezes'). It does not name alternative tools or provide explicit when-not-to-use guidance, so it stops short of a 5.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals an important behavior beyond searching: it validates the check digit before executing the search and treats invalid CNPJ as a likely photo-reading error. The read-only nature is implied by 'Busca' but not explicitly stated.

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

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

The description is two concise sentences with information front-loaded: first the core search purpose, then the validation behavior and fallback action. There is no filler or redundant restatement.

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 search tool with no output schema, the description covers what it searches, by which identifiers, and what to do when validation fails. It could more explicitly state that at least one identifier parameter should be provided, but overall the operational guidance is strong.

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

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

Schema coverage is 100%, with each parameter already described as 'com ou sem máscara.' The description adds a small behavioral note about CNPJ validation, but it does not substantially expand on the schema's parameter definitions. Baseline 3 is appropriate given the high schema coverage.

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

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

The description uses a specific verb and resource: 'Busca o fornecedor (credor) no Sienge por CNPJ, CPF ou nome.' It clearly identifies the system, the entity being searched, and the available search keys. This makes it easy to distinguish from siblings like buscar_titulos or criar_credor.

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

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

The description gives clear context for when to use the tool and even provides a workflow for invalid CNPJ input: check the photo or ask the user for the number. It does not explicitly compare against alternatives such as criar_credor or verificar_documento, so it stops short of full exclusion 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?

Sem annotations disponíveis, a descrição carrega o peso da transparência. Ela comunica que a operação é uma busca e identifica período obrigatório e filtros opcionais, mas não informa formato de retorno, limite de resultados, paginação ou ausência de efeitos colaterais. O comportamento básico é claro, mas há lacunas relevantes.

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?

Duas frases diretas e sem redundância. A informação essencial — recurso, obrigatoriedade do período e filtros opcionais — é apresentada logo no início, e cada frase contribui com valor.

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

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

A descrição é suficiente para selecionar e invocar a ferramenta: recurso, parâmetros obrigatórios, filtros opcionais e casos de uso. No entanto, não há schema de saída e a descrição não detalha o formato do retorno nem o parâmetro 'limite', o que compromete a completude contextual.

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 adiciona significado ao mapear período de emissão e filtros opcionais (credor, número do documento, empresa, centro de custo), compensando parcialmente a baixa cobertura de descrições no schema. Porém, o parâmetro 'limite' não é mencionado na descrição nem está documentado no schema, deixando o agente sem conhecer a restrição de máximo 200.

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 usa verbo específico e recurso claro: 'Busca títulos do contas a pagar'. Também menciona os filtros opcionais e o propósito final de conferir duplicidade ou achar um título lançado. Não diferencia explicitamente de irmãs como consultar_titulo ou verificar_documento, mas o escopo e o caso de uso dão direção 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?

A descrição afirma explicitamente quando usar: 'Use para conferir duplicidade ou achar um título lançado'. Isso fornece contexto claro, embora não declare quando não usar nem aponte alternativas entre as ferramentas irmãs.

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?

With no annotations, the description itself communicates a read operation via 'Lê' and discloses optional attachment/installment behavior. It does not mention return format, error behavior, or permissions, but for a read-only lookup the core transparency is adequate.

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

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

The description is two short sentences, front-loading the operation and ending with a practical use case. No filler or redundancy.

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

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

For a simple read tool, the description covers purpose and usage, but with no output schema and no annotations, it leaves return structure and edge cases (e.g., not found) unstated. It is adequate for a straightforward verification call but not 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?

The description clarifies that titulo_id is the title number and that com_parcelas/com_anexos control inclusion of installments and attachments. However, the schema already documents the booleans, and titulo_id is only described as 'número' without further type or source detail, so added value is moderate.

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 the specific verb 'Lê' (reads) and identifies the resource as a Sienge título, queried by number with optional installments and attachments. It clearly describes a single-title lookup, which separates it from sibling list/search tools, though it does not explicitly name 'buscar_titulos' as the alternative.

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

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

The description explicitly advises using the tool 'para provar que o lançamento entrou como esperado' (to verify an entry was posted), giving a concrete use case. It does not provide exclusions or mention alternatives such as buscar_titulos, so it stops short of full when-not 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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals a critical safety requirement (confirmado:true), explicitly warns not to call before user approval, and discloses idempotent duplicate behavior ('devolve o existente sem duplicar'). This provides meaningful insight beyond the raw schema.

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

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

The description is concise and well-structured: two sentences, with the key safety prerequisite front-loaded and the duplicate behavior stated second. Every sentence adds critical information without redundancy.

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

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

The description covers the essential invocation condition and duplicate behavior, but it does not address the full parameter set, return values, or error conditions. Given the 9 parameters图示, no output schema, and no annotations, a more complete description is necessary for fully reliable use. 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?

Schema coverage is only 44%, so the description needs to compensate for undocumented parameters. It adds context about the duplicate check based on 'documento' (cpf/cnpj) and emphasizes confirmado, but it does not explain parameter relationships, required formats, or the role of fields like telefone and inscricao_estadual. This is insufficient for a 9-parameter tool.

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

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

The description states a specific action ('Cadastra') and a clear resource ('um fornecedor (credor) no Sienge'). This clearly distinguishes it from sibling tools like buscar_credor, verificar_documento, and criar_titulo, which have different purposes.

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

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

The description gives an explicit precondition: 'Exige confirmado:true — só chame depois que o usuário aprovou no chat.' This tells the agent when it is appropriate to invoke the tool. It does not explicitly mention alternatives or when not to use it, but the guidance is clear and actionable.

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?

With no annotations provided, the description carries the full burden and does so well. It discloses the confirmation requirement, the automatic duplicate check (same creditor + document number within ±60 days), the refusal behavior, and the accepted date/number formats. This goes well beyond the schema and gives the agent critical operational 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 compact and front-loaded: the core action comes first, followed by the confirmation gate, duplicate policy, and formatting rules. Every sentence adds essential operational information and there is no filler or repetition of the schema.

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

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

For a complex creation tool with no output schema or annotations, the description provides the key context needed to invoke it correctly: preconditions, duplicate handling, and value formats. It could additionally describe the return value or post-creation outcome, but the information critical to a correct call is present.

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

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

Schema coverage is only 53%, so the description must compensate. It adds meaningful global guidance for date parameters (DD/MM/AAAA or AAAA-MM-DD), numeric values (1.234,56), and explains the behavior of ignorar_duplicidade, which the schema does not describe. It does not individually document every parameter, but the high-leverage formatting rules cover the most error-prone ones.

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

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

The description states a specific action ('Lança um título'), the resource ('contas a pagar do Sienge'), and the endpoint ('POST /bills'). This makes the tool's purpose immediately clear and distinguishes it from lookup-oriented siblings like buscar_titulos and consultar_titulo.

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 explicitly states when the tool may be called: only after showing the summary and receiving user confirmation, and with confirmado:true. It also explains when duplicate refusal can be bypassed with ignorar_duplicidade. However, it does not explicitly name alternatives or state when not to use this tool versus related creation/lookup 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?

With no annotations, the description carries the behavioral burden and it does so well by disclosing a 24h cache, the quota-saving rationale, and the refresh mechanism. It doesn't mention return format or error behavior, but the operation is presented as a simple list.

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

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

Two sentences, no filler; the purpose and filters come first, followed by cache/refresh behavior. Every sentence earns its place.

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

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

For a low-complexity optional-parameter list tool, the definition covers the core call decisions: what is listed, available filters, and cache freshness. It omits return-shape and pagination details, but those are not necessary 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 schema already documents all three parameters (100% coverage), so baseline is 3. The description maps 'texto' and 'empresa' to the filters and clarifies atualizar's purpose with the 24h cache detail, but adds little beyond the schema.

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

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

States a specific action ('Lista') on a specific resource ('centros de custo do Sienge') and gives examples of what counts (obras, departamentos, administrativo). It is clearly not a generic list, though it doesn't explicitly separate itself from sibling listar_departamentos.

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 tells the agent the tool lists cost centers and explains when to pass atualizar:true to bypass the cache. It does not, however, give explicit guidance about when to prefer this over sibling listing tools or when not to use it.

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

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

With no annotations, the description carries the behavioral burden. It does disclose an important behavior: 'Cache de 24h', indicating results may be stale for up to 24 hours. However, it does not clarify whether the operation has side effects, how the 'atualizar' parameter interacts with the cache, or any permissions needed.

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 short and front-loaded with the main purpose. The unclear parenthetical phrase 'apropriação opcional do título' prevents a perfect score because it does not clearly earn its place.

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

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

For a tool with no annotations, no output schema, and an undocumented parameter, this description is not complete enough for confident invocation. It omits what 'atualizar' does, what the response contains, and whether the cache can be bypassed.

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

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

Schema description coverage is 0% and the description never explains the boolean parameter 'atualizar'. The cache note hints that refreshing may be possible, but the connection is not explicit, so the description fails to compensate for the undocumented schema.

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

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

The description states a specific verb and resource: 'Lista os departamentos do Sienge', which clearly distinguishes this from sibling list tools by domain object. However, the parenthetical 'apropriação opcional do título' is ambiguous and adds noise without clarifying scope.

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

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

There is no guidance about when to use this tool versus sibling list tools such as listar_empresas or listar_centros_custo. No exclusions, prerequisites, or alternative routing are provided; usage is only weakly implied by the verb 'Lista'.

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?

With no annotations, the description carries the transparency burden; it makes clear this is a read-only listing operation ('Lista') and specifies the output fields (código, nome, nome fantasia, CNPJ). It does not discuss pagination or sorting, but for a zero-parameter listing tool this is sufficient.

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

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

Two short sentences with no filler: the first states the action and output, the second gives the use case. Key information is front-loaded.

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

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

For a simple zero-parameter list tool with no output schema, this description is complete: it names the entity, qualifier, output fields, and intended use case. Nothing needed for correct invocation 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?

There are no parameters to document, so the schema is exhaustively covered and the baseline of 4 applies. The description's mention of the returned fields adds useful context beyond the empty schema.

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

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

The description uses a specific verb ('Lista') and resource ('empresas cadastradas no Sienge'), enumerates the exact fields returned, and adds the clarifying 'devedoras' qualifier. This makes it distinguishable from sibling list tools such as listar_departamentos or listar_centros_custo.

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 explicitly states its intended use: selecting the default company for lançamentos. It does not name alternatives or exclusion conditions, so it stops short of a 5.

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

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

No annotations are provided, so the description carries the burden of behavioral disclosure. 'Lista' conveys a read-only listing operation and the setup context adds useful behavioral framing. However, it does not disclose the effect of the optional 'atualizar' parameter, such as whether it forces a refresh or changes output.

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

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

The description is two short, efficient sentences. The main purpose is front-loaded, and the setup directive earns its place. There is no filler or redundant restating of the tool name.

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 list operation with one optional boolean parameter and no output schema. The description is adequate for basic invocation and context, but the undocumented 'atualizar' parameter is a real gap, and there is no mention of what the returned data looks like. Additional detail would make it 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%, and the description never mentions the 'atualizar' parameter. The agent is left to guess whether it means update the cache, re-fetch from Sienge, or something else. The description adds no meaning beyond the raw schema field.

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 lists Sienge indexadores, adding relevant context that a title needs one and that 'Real' is the typical value. It is specific enough to identify the resource, though it does not explicitly distinguish itself from the sibling listar_* 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 gives explicit usage context: use it during setup to define SIENGE_INDEXADOR_PADRAO. It does not mention when not to use it or alternatives, so it falls short of the highest level, but the guidance is clear and actionable.

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?

Não há annotations, então a descrição carrega o peso da transparência. Ela revela comportamentos relevantes: cache de 24h, override via atualizar:true, e filtro padrão para contas ativas/de resultado que recebem lançamento. Não cobre paginação ou autenticação, mas para uma operação de listagem esses detalhes são substanciais.

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?

Duas frases compactas: propósito primeiro, comportamento padrão em segundo, cache por último. Não há enrolação, repetição de schema ou informação irrelevante.

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

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

Para uma ferramenta de listagem com 4 parâmetros opcionais e nenhum obrigatório, a descrição cobre propósito, escopo padrão, cache e semântica dos parâmetros relevantes. Não há schema de saída nem menção a formato de resposta/paginação, mas nada essencial para invocar corretamente está ausente.

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?

O schema já documenta busca, somente_ativos e incluir_totalizadoras (75% de cobertura), mas a descrição adiciona significado ao parâmetro atualizar ('força a busca') e explica por que totalizadoras ficam fora por padrão ('não recebem lançamento'). Isso vai além do 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?

A descrição abre com o verbo específico 'Lista' e o recurso 'plano financeiro (categorias de despesa/receita) do Sienge', definindo claramente o objeto. Isso a distingue imediatamente de irmãos como listar_departamentos e listar_centros_custo, sem ambiguidade.

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 informa o contexto de uso padrão: contas ativas e de resultado, cache de 24h e atualizar:true para forçar busca. Porém, não menciona alternativas, nem quando evitar esta ferramenta ou preferir uma irmã; o uso é implícito, não explicitamente direcionado.

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?

No annotations are provided, so the description carries full behavioral disclosure. It transparently states that it reads .env, makes a real API call (company list), and summarizes what is configured and what is missing. It doesn't explicitly state non-destructiveness or failure behavior, but the diagnostic nature makes the main traits clear.

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

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

Two dense sentences with no filler. The main check and behavioral details are front-loaded, and the usage directive is given as a short closing sentence. Every word contributes value.

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

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

For a zero-parameter diagnostic tool with no output schema, the description fully explains what inputs it uses (.env), what it does (real API call), and what it returns (summary of patterns and missing items). An agent can correctly invoke and interpret the 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, so the description correctly adds no parameter-specific details. This matches the baseline for a parameterless 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?

Description uses a specific verb ('Confere') and resource (Sienge configuration/accessibility), enumerates concrete actions (reads .env, makes a real call, summarizes patterns) and clearly distinguishes itself from the listar_* siblings as a status/diagnostic tool.

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

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

Explicitly instructs 'Primeira coisa a chamar numa sessão' (call first in a session), giving a clear when-to-use directive. It does not mention when not to use it or point to alternatives, but for a status check this is sufficient 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool does not spend an API request, that it draws on local config files (aprendizado.json and regras.json), and that it may return no suggestion as a possible outcome with a clear fallback action. This is meaningful behavioral context, though it stops short of stating whether it performs any writes or side effects.

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

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

The description is three short sentences, each earning its place: purpose, cost characteristic, and fallback. It is front-loaded with the core action and contains no redundant or filler wording.

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 low-to-medium complexity, optional parameters, and absence of an output schema, the description is nearly complete for an agent to call the tool correctly. It explains what the tool suggests, the data sources it uses, that it incurs no request cost, and how to handle a missing suggestion. The only minor gap is that it does not explicitly describe the structure of a successful suggestion response, but 'sugere centro de custo e plano financeiro' implies the response contains those 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?

Schema coverage is 60% (itens, descricao, fornecedor have descriptions; cpf and cnpj do not). The description adds little parameter-level detail beyond naming the 'fornecedor' history as the source of suggestions. It does not clarify the relationship or precedence between cpf, cnpj, and fornecedor, nor how itens/descricao influence the suggestion. The parameter names are fairly self-evident, so a baseline 3 is appropriate.

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

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

The description opens with a specific verb and resource: 'Sugere centro de custo e plano financeiro para a despesa'. This immediately distinguishes it from sibling tools like listar_centros_custo or aprender_apropriacao, which are listing or learning operations rather than suggestion operations.

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

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

The description gives clear context: the tool is appropriate when there is confirmed supplier history and user rules, and it explicitly notes that it does not consume a request. It also provides a conditional behavior ('Sem sugestão = pergunte ao usuário'), which helps an agent decide whether to ask the user. However, it does not explicitly name alternatives or say when NOT to use it beyond the no-suggestion branch.

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?

With no annotations, the description carries the full burden. It discloses two non-obvious behaviors: the API only supports per-code queries and each code costs one API request. It does not spell out the return shape or error behavior, but the read-only/query nature is conveyed by 'só consulta por código.'

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 cover purpose, API constraint, and intended use. Every sentence earns its place, and the most decision-relevant constraints are 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?

For a single-optional-parameter setup tool with no output schema, the description covers what it does, the API limitation, request cost, and intended use. The only minor omission is an explicit description of the return format, which is only implied by 'Confere quais códigos ... existem.'

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

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

The input schema already documents the codigos array and the default list, so schema coverage is 100%. The description adds value by linking the parameter to request cost and to the SIENGE_DOCUMENTO_PADRAO outcome, which the schema alone does not convey.

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 ('Confere') and a specific resource ('códigos de tipo de documento no Sienge'), with concrete examples (NF, NFE, CF, REC). It also distinguishes the tool from listar_* siblings by stating that the API has no listing endpoint, so the purpose 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?

It explicitly anchors the tool to setup: 'Use no setup para definir SIENGE_DOCUMENTO_PADRAO.' It also warns that there is no list endpoint and each tested code consumes a request, which implies a narrow test-a-few-codes use case. It does not name an alternative tool or a broader when-not condition, so it stops short of a full 5.

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