Server Quality Checklist

Tool Scores

• carregar_comprasA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It explains that the tool loads purchase tools with resolved data, which provides context, but it does not explicitly state whether this is a read-only operation or if there are side effects. Since 'carregar' implies loading, it's likely harmless, but this is not made explicit.

  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 two sentences, front-loaded with the main action and content, followed by usage guidance. Every sentence earns its place with no redundancy or fluff.

  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 zero-parameter tool with no output schema, the description is fairly complete: it states what the tool does and when to call it. It lacks details about return values or prerequisites like authentication, but given the simplicity and the existence of sibling tools like verificar_autenticacao, it is sufficiently contextual.

  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 zero parameters, and the schema coverage is 100%. According to the baseline rule, 0 parameters merit a baseline of 4. The description adds no parameter details because none exist, which 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 clearly states the verb 'Carrega' (loads) and the resource 'ferramentas de compras' (purchase tools), and specifies the content loaded (queue of pending approvals with resolved items, inputs, suppliers, and works). It distinguishes itself from siblings by focusing on loading the purchasing context rather than testing connections or explaining processes.

  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 explicitly says 'Chame quando a conversa for sobre pedidos de compra, aprovação ou fornecedores' (call when the conversation is about purchase orders, approval, or suppliers), providing clear when-to-use guidance. However, it does not mention alternatives or when-not-to-use, so it misses the full 5-level specificity.

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

• consultar_cotaA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that there are two independent quotas (REST and BULK), that BULK is consumed by specific operations and exhausts first, and that balance calculation requires the SIENGE_MCP_API_PACKAGE environment variable. This exceeds baseline expectations for a simple status tool.

  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 compact and front-loaded: the main purpose appears in the first sentence, followed by essential operational details (quota types, consumption patterns, configuration requirement). Every sentence earns its place without redundancy.

  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?

  For a zero-parameter, no-output-schema tool, the description is remarkably complete. It explains what the tool shows, when to use it, the behavior of the two quotas, and a critical prerequisite. An agent has all necessary information to select and invoke the tool correctly.

  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 zero parameters, so the schema is complete by definition. The description appropriately focuses on what the tool reports rather than parameter details, matching the baseline for 0-parameter tools.

  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: to show consumption and balance of the Sienge API's daily quotas. It uses a specific verb ('Mostra'), identifies the resource (daily quotas), and naturally distinguishes itself from sibling tools like connection tests and purchase loaders.

  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 explicitly instructs to 'Consulte antes de uma sequência dessas consultas' (consult before a sequence of these queries), giving a concrete use case. It does not mention exclusions or alternatives, but given the sibling tools are unrelated, the usage context is clear.

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

• testar_conexaoA
  4.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description bears the full burden. It discloses key behavioral traits: the tool performs a real API call ('chamada real') and is low-cost ('baixo custo'). However, it does not explicitly state whether the call has side effects or how results are returned, though the nature of an authentication test implies a read-only check. This is useful but not fully transparent.

  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 two sentences long, front-loaded with the core purpose, and then provides usage guidance with an alternative. Every sentence earns its place with no redundancy or fluff.

  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?

  Given the tool's simplicity (no params, no output schema), the description is nearly complete: it tells what it does, when to use it, and how it differs from the sibling. The only gap is the lack of explicit return-value or success/failure behavior, which the agent might need to know since there is no output schema to clarify it.

  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 zero parameters, so the schema already covers everything (100% coverage vacuously). The description adds no parameter details, but none are needed. Baseline for 0 parameters is 4, and the description does not detract from that.

  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: to test whether credentials actually authenticate against the Sienge API via a real, low-cost call. It uses a specific verb ('Testa') and resource ('credenciais contra a API do Sienge'), and distinguishes itself from the sibling tool 'verificar_autenticacao' by noting that this one makes a real API call.

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

  Usage Guidelines5/5

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

  The description explicitly provides use cases: 'Use para diagnosticar falha de conexão ou credencial' (use to diagnose connection or credential failure). It also gives a clear alternative: 'para apenas ver qual mecanismo está configurado, sem chamar a API, use verificar_autenticacao'. This meets the highest standard of when/when-not guidance.

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

• verificar_autenticacaoA
  4.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that the tool does not call the API, which is a key behavioral trait (non-side-effect). It also describes what it shows (mechanism and credential completeness). It could add more detail about return format or edge cases, but for a simple inspection tool, this is sufficient transparency.

  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 two sentences with no wasted words. It front-loads the main purpose, then adds the critical exclusion and alternative tool reference. Every sentence earns its place.

  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?

  For a simple tool with no parameters and no output schema, the description is complete: it explains what the tool displays, what it does not do (call the API), and directs to the sibling tool for functional verification. No further context is needed.

  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 has zero parameters, and schema coverage is trivially 100%. The baseline for 0 parameters is 4, and the description does not need to explain parameters since there are none. It adds no parameter-related info, which 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 clearly states the tool's function: showing which authentication mechanism is configured (Bearer Token or Basic Auth) and whether credentials are complete. It uses a specific verb ('Mostra') and resource ('autenticação configurada'), and explicitly distinguishes itself from the sibling tool 'testar_conexao' by noting it does not call the API.

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

  Usage Guidelines5/5

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

  The description provides explicit usage guidance: it tells the agent when to use this tool (to inspect configuration) and when not to (to verify actual functionality), directing to the alternative 'testar_conexao' for actually testing credentials. This meets the 'when/when-not/alternatives' criterion perfectly.

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

• explicar_processo_comprasA
  4.9/5.0
  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 of behavioral disclosure. It is transparent about what the tool returns: a staged explanation of the purchase process, including optional steps, valid paths, API limits, and which stages are actually covered by server tools ('nem toda etapa do processo é coberta'). This sets accurate expectations about the tool's advisory role.

  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 concise, well-structured, and front-loaded with the primary purpose. Each sentence earns its place: the first defines scope, the second gives usage guidance and error prevention, and the third sets expectations about tool coverage. No fluff or redundancy.

  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?

  For a zero-parameter tool with no output schema, the description is remarkably complete. It explains what the tool does, when to use it, what content it will provide, and its limitations. The sibling tool names further clarify the context, making this description fully sufficient for an agent to select and invoke the tool correctly.

  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 zero parameters, so the baseline for this dimension is 4. The description appropriately does not waste space on parameter details; it focuses on the tool's purpose and output, which is all that is needed for a no-input advisory tool.

  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 the tool's specific purpose with a clear verb ('Explica') and resource ('processo de compras do Sienge'), and goes further to specify the content (5 etapas, opcionais, caminhos válidos, limites da API). It clearly distinguishes itself from sibling tools, which perform data retrieval or connection tests, by positioning itself as a process guide.

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

  Usage Guidelines5/5

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

  The description gives explicit usage direction: 'Consulte ANTES de responder qualquer pergunta sobre solicitações, cotações, pedidos de compra ou aprovações.' It also mentions common pitfalls to avoid, which helps the agent decide when to use this tool before attempting data queries, and notes that the tool identifies which stages have actual tool coverage.

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