Server Quality Checklist

Tool Scores

• obter_schema_xmlA
  3.6/5.0
  Behavior2/5

  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 explains what the schema contains but does not state whether authentication is required, what the response looks like, whether the operation has side effects, or how errors are surfaced.

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

  Conciseness4/5

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

  The description is compact and front-loaded with the core purpose. The parameter recap is somewhat redundant with the schema, but it is short and helps confirm the optional parameters at a glance. No unnecessary elaboration.

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

  Completeness3/5

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

  Core invocation context is present: required parameter, optional parameters, and a clear use case before enviar_registros. However, there is no output schema and the description does not specify how the XSD is returned or what the agent should expect as a result, which would make the tool more self-sufficient.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents all parameters. The description adds minimal value by clarifying that 'entidade' is a slug and grouping the optional auth/environment parameters, but it does not deepen semantic understanding beyond the schema.

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

  Purpose5/5

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

  The description uses a specific verb ('Obtém') and resource ('schema XSD de uma entidade'), and clarifies the purpose: validating XML before submission. It is clearly distinct from sibling tools like listar_entidades, enviar_registros, and obter_status.

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

  Usage Guidelines4/5

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

  It explicitly says to use this tool to check the expected XML structure before calling 'enviar_registros', which gives a concrete trigger. It does not discuss when not to use it or contrast it with other sibling tools, so it stops short of full alternative routing.

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

• enviar_registrosA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses that the tool performs mutations (insert/update/delete), requires XML conforming to an XSD schema, and returns a ticket for async tracking. However, it does not disclose side effects, idempotency, error behavior, or whether the operation is synchronous or asynchronous beyond the ticket return.

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

  Conciseness4/5

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

  The description is well-structured with a clear opening sentence, a short XML guidance paragraph, a parameter list, and a return-value note. It is slightly longer than necessary but every section earns its place; the parameter list partially duplicates the schema.

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

  Completeness4/5

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

  For a mutation tool with no annotations and no output schema, the description covers the essential context: what the tool does, how to structure the XML, how to validate it, and how to track the result. It lacks explicit error-handling or rollback behavior, but the ticket-based flow is clearly communicated.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents all five parameters. The description adds a bit of context (e.g., DbAcao field semantics, example slugs) but does not significantly go beyond the schema. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description states a specific verb ('Envia'), a resource ('registros em XML'), and a destination ('Claro Gerencial WebService de Input'). It also explicitly lists the three operations it supports (inserir, alterar, excluir), which distinguishes it from sibling tools like obter_registros (read) and obter_status (status polling).

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

  Usage Guidelines4/5

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

  The description gives clear context: use it to insert, update, or delete records, and mentions the DbAcao field for operation type. It also references obter_schema_xml for validation and obter_status for tracking, but it does not explicitly state when NOT to use it (e.g., for reading data, use obter_registros).

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

• gerar_arquivoA
  4.2/5.0
  Behavior4/5

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

  The description discloses a key behavior: the file will be available within 2 hours, indicating an asynchronous operation. It also mentions that optional credentials fall back to environment variables, providing insight into authentication. Since no annotations are provided, this description carries the full burden and addresses the most critical behavioral aspects.

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

  Conciseness4/5

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

  The description is compact, with a clear purpose in the first sentence and a concise parameter list. It avoids unnecessary detail while covering the essential points. The structure is logical, though it repeats some schema information, it does so in a readable format.

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

  Completeness3/5

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

  While the description covers the operation and timing, it does not explain what the tool returns (e.g., a status or confirmation) nor error scenarios. Since there is no output schema, this is a gap. However, for a simple tool that primarily triggers an FTP file generation, the description is mostly sufficient, but missing return info lowers completeness.

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

  Parameters4/5

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

  The input schema already has 100% description coverage for all parameters. The description adds semantic relationships: the ticket and entidade must match those from 'obter_registros', and the optional usuario/senha/ambiente default to environment variables. This goes beyond the schema's basic descriptions, enhancing parameter understanding.

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

  Purpose5/5

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

  The description clearly states the tool generates an FTP file from records previously obtained via 'obter_registros', specifying the verb (gera), resource (arquivo FTP), and the dependency on a prior step. It distinguishes itself from siblings like obter_registros (which retrieves data) and enviar_registros (which sends data).

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

  Usage Guidelines4/5

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

  It explicitly instructs to use the ticket returned by 'obter_registros', implying the prerequisite call. It does not explicitly list alternatives, but the context makes it clear this is for generating an FTP file after fetching records. No exclusion is given, but the guidance is sufficient for proper sequencing.

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

• obter_statusA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It provides a comprehensive list of status codes and explains that when status=9, the 'Conteudo' field contains the detailed log. This gives the agent a clear picture of the tool's output semantics and processing lifecycle, though it doesn't mention polling behavior or error-handling recommendations.

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

  Conciseness5/5

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

  The description is well-structured and front-loaded: the core purpose and usage context appear in the first sentence, followed by a compact but valuable status-code list. Each status code is meaningful for the agent's decision-making, and the final note about status=9 and 'Conteudo' is relevant and concise.

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

  Completeness4/5

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

  The tool has no output schema and no annotations, so the description must cover expected response behavior. It explains the meaning of all status codes and the special log behavior at status=9, which is sufficient for a status-polling tool. It could be more complete by describing the response shape for error statuses or suggesting when to stop polling, but the essential context is present.

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

  Parameters3/5

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

  The input schema already documents all 5 parameters with 100% coverage, so the baseline is 3. The description reinforces that 'ticket' comes from 'enviar_registros', which is already stated in the schema. It doesn't add new parameter-level semantics beyond what the schema provides, but it also doesn't need to.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Consulta o status de um envio de registros pelo ticket', identifying both the action (consulta status) and the resource (envio de registros identified by ticket). It also references the related 'enviar_registros' flow, which distinguishes this status-checking tool from the other sibling tools.

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

  Usage Guidelines4/5

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

  It explicitly says 'Use após enviar_registros para acompanhar o processamento', giving a clear usage context and indicating the sequential relationship with the submission tool. It doesn't list alternatives or exclusion criteria, but the sibling tools are distinct enough that this 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.

• listar_entidadesA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full behavioral burden. It states that the tool lists all available entities and indicates which support query (output) and which support sending (input). This gives the agent a meaningful expectation of the response content beyond the empty input schema. It does not describe format or limitations, but for a zero-parameter discovery tool this is largely adequate.

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

  Conciseness5/5

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

  Two concise sentences. The first states the action and result, the second provides the usage instruction. Every sentence adds value and the key information is front-loaded.

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

  Completeness4/5

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

  For a simple, zero-parameter discovery tool, the description is nearly complete. It explains purpose and when to use it, and hints at the return semantics. It lacks a formal output schema, but the text adequately prepares the agent for what will be returned.

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

  Parameters4/5

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

  The tool has no parametersced, so the baseline is 4. The description does not need to explain parameters because there are none, and the schema is empty.

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

  Purpose5/5

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

  The description specifies a clear action ('Lista todas as entidades disponíveis') and a concrete resource ('Claro Gerencial'). It also states what the tool reveals about each entity (output/input support), which separates it from the sibling tools that operate on specific records, files, or statuses.

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

  Usage Guidelines4/5

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

  The description gives explicit usage context: 'Use esta ferramenta para descobrir quais entidades existem antes de usar as demais.' This clearly tells the agent when to call it—before other tools—and implies it is a discovery/preflight step. It does not explicitly name alternatives or conditions for not using them, but the guidance is sufficient.

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

• obter_registrosA
  4.6/5.0
  Behavior5/5

  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 that the tool returns a ticket rather than direct data, that pagination may require repeated calls with completa=False until an empty result, and that authentication/ambient values fall back to environment variables. This gives the agent important non-obvious behavior beyond the schema.

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

  Conciseness4/5

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

  The description is front-loaded with the core purpose, followed by a well-organized parameter list and then the critical return/pagination behavior. It is a bit longer than strictly necessary because it partially repeats schema information, but each section earns its place by adding operational context.

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

  Completeness5/5

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

  Despite having no output schema and no annotations, the description provides everything needed to invoke the tool correctly: required parameters, optional parameters, defaults, return format, and how to handle pagination. It also connects to sibling tools in the workflow. No critical operational information is missing.

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

  Parameters4/5

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

  The schema already covers all parameters at 100%, but the description adds genuine value: concrete examples for 'entidade', a clearer explanation of 'completa' (full vs incremental loads), and explicit env-var defaults for 'usuario', 'senha', and 'ambiente'. This goes beyond the schema descriptions without making them redundant.

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

  Purpose5/5

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

  The description uses a specific verb and resource: 'Obtém registros de uma entidade do Claro Gerencial.' It clearly frames the tool as a data consultation/download and references the related workflow tools 'listar_entidades' and 'gerar_arquivo', which helps distinguish it from siblings like 'enviar_registros' and 'obter_status'.

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

  Usage Guidelines4/5

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

  It explicitly states this tool is for consulting/downloading data and gives practical usage context: use 'listar_entidades' to discover valid entity slugs and use the returned ticket with 'gerar_arquivo'. It also provides pagination guidance by explaining when to call again with completa=False. It does not explicitly exclude alternative tools, but the context is clear enough.

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