Server Quality Checklist

Tool Scores

• research_webA
  4.1/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it delivers: it discloses that the tool internally reformulates the query into multiple search angles, runs them in parallel, reads the best pages, and summarizes. It also reveals that calling again with the same question yields no new material, which is a significant behavioral trait. This goes far beyond a basic purpose statement and provides actionable insight for the agent.

  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 ('Pesquisa na web e devolve um resumo com fontes') and then provides essential usage and behavioral guidance. It is somewhat verbose, especially the repeated explanation of one-call-per-question, but every sentence adds value. It is well-structured into coherent paragraphs, though it could be tightened.

  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?

  The tool is relatively simple (search + summarize), and the description covers when to use it, how to phrase the query, and the one-call-per-question rule. The output schema exists, so the description does not need to explain return formats. Annotations are absent, but the description provides all necessary behavioral context for an agent to call the tool correctly. Nothing essential is missing.

  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 coverage is 100% – both 'query' and 'recent' have detailed descriptions in the schema. The description's instructions on passing the full natural-language query are already present in the schema, so it adds little over the structured definitions. The baseline of 3 is appropriate because the schema already explains parameters thoroughly.

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

  Purpose4/5

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

  The description clearly states the tool 'Pesquisa na web e devolve um resumo com fontes' (searches the web and returns a summary with sources), which is a specific verb and resource. It clearly differentiates from 'read_url' and 'analyze_urls' by focusing on autonomous searching rather than processing given URLs, though it does not explicitly name the siblings. 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.

  Usage Guidelines4/5

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

  The description gives explicit when-to-use guidance: 'Use para qualquer informação que você não saiba com certeza' and 'quando acha que sabe mas o assunto pode ter mudado' – effectively stating to use this tool instead of memory when uncertain or potentially outdated. It also provides a clear when-not-to-call repeatedly: 'Só chame outra vez quando a pergunta for genuinamente outra'. However, it does not explicitly mention alternatives like read_url or analyze_urls, 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.

• analyze_urlsA
  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 behavioral burden and does meaningful work: it discloses that full page content will not enter the agent's context and that only the analysis result returns. It does not cover error or failure behavior, but for a URL-reading tool the key privacy/context behavior is clearly disclosed.

  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 three sentences with no filler: a crisp purpose statement, a usage condition list, and an explicit pointer to the alternative tool. It is front-loaded and 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?

  The output schema covers return shape, the input schema fully documents both parameters, and the description covers when to use the tool, when to avoid it, and what behavioral guarantee to expect. Although research_web is not named, the phrase 'quando o usuário fornecer a(s) URL(s)' clearly separates this tool from web research.

  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% and the schema already documents URL count, ordering, comparison usage, the request default, and examples. The description reinforces the comparison use case but does not add significant parameter-level meaning beyond what the schema provides, so the baseline score of 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 first sentence states a specific verb ('Lê'), resource ('URLs'), and outcome ('devolve uma análise pronta, sem o texto bruto'), which makes the tool's function unambiguous. The negative clause about raw text also distinguishes it from read_url.

  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 says when to use the tool ('quando o usuário fornecer a(s) URL(s) e quiser resumo, parecer técnico, opinião ou comparação') and names the alternative for the opposite case ('Prefira read_url apenas quando o texto completo da página for necessário de verdade'). This gives the agent clear routing guidance.

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

• read_urlA
  4.7/5.0
  Behavior5/5

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

  Não há annotations, e a descrição assume integralmente o papel de transparência. Ela revela que uma página por chamada é lida, que o texto bruto inteiro entra no contexto, que o retorno inclui cabeçalho 'Fonte desta página' com link markdown pronto, e que não há resumo interno — comportamento relevante para o agente saber o que esperar.

  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?

  Embora mais longa que o mínimo, cada frase agrega valor: scopo, aviso de contexto, alternativa, instrução de citação e comparação com o irmão. A informação essencial está na frente e a estrutura é clara, sem redundância.

  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?

  Para uma ferramenta com um único parâmetro, output schema presente e um irmão alternativo, a descrição cobre uso, diferenças, retorno e implicações de contexto. Nada essencial para selecionar e invocar corretamente está ausente.

  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?

  Há apenas um parâmetro, url, com description no schema cobrindo 100% do significado ('O endereço completo da página (http/https)'). A descrição do tool acrescenta pouco além de reforçar que é uma URL específica, então o baseline 3 é adequado já que o schema faz o trabalho.

  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?

  A descrição usa verbo específico ('Abre uma URL específica') e recurso claro ('devolve o conteúdo principal da página'), diferenciando-se imediatamente dos irmãos: analyze_urls lê várias páginas e research_web faz busca/resumo. A função e o escopo de uma chamada ficam inequívocos.

  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?

  Há orientação explícita de quando usar: 'quando o usuário fornecer um link e pedir para você ler, resumir, analisar ou extrair algo dele'. Também indica explicitamente a alternativa para múltiplas páginas ('encadear read_url gasta contexto e tempo à toa') e a diferença frente a research_web, que não faz busca nem resumo interno.

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