Fronteira de confiança (classificação LOCAL, preserva privacidade). NÃO recebe a pergunta: devolve a RUBRICA para VOCÊ (assistente) classificar a pergunta do usuário no seu próprio contexto, sem enviá-la ao servidor. Bandas: 'inferivel' (pode rodar), 'arriscado' (rode com ressalva), 'humano' (NÃO pergunte a persona sintética — exige estado vivido). Aplique antes de preparar_pesquisa.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries behavioral disclosure. It explains that the tool does not receive the user question (no input), returns a rubric for local classification, and lists the bands with their meanings. It does not mention output format or side effects, but the behavior is well-articulated.
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?
Description is a single concise paragraph with clear information: purpose, privacy, behavior, bands, and usage order. No unnecessary words, but could benefit from bullet-pointing the bands for faster parsing. Still efficient.
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 no output schema, the description adequately explains the return value (a rubric with specific bands). It tells the assistant to use the rubric to classify locally. However, it does not specify the exact format of the rubric (e.g., JSON or string), which might require agent inference. Nearly 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?
Input schema is empty (0 parameters). Baseline is 4 as per guidelines. The description adds context that the tool does not accept the question as input, which clarifies why there are no parameters. It explains the rubric's structure (bands) beyond what the schema conveys.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: it provides a trust boundary rubric for classifying user questions locally, preserving privacy. It specifies the verb ('devolve a RUBRICA'), the resource ('classificação LOCAL'), and distinguishes itself from siblings like 'preparar_pesquisa' by being a prerequisite.
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 states 'Aplique antes de preparar_pesquisa', giving a direct when-to-use instruction. It also provides guidance on when not to use certain bands ('humano' band) and clarifies the local, private nature of the tool, helping the agent decide between this and tools that send data to a server.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: overview, fact search, persona filtering, persona details, sampling, survey preparation, confidence assessment, distributions, institution info, and voice examples. No two tools overlap significantly.
Most tools follow a verb_noun pattern, but some use English prefixes (get_) while others use Portuguese verbs (avaliar_, buscar_). This inconsistency could cause confusion, though the names are still readable.
10 tools is appropriate for the synthetic panel domain. Each tool serves a distinct function without redundancy, and the count is neither too few nor too many.
The tool set covers the full workflow: overview, question classification, fact retrieval, persona filtering and display, sampling, survey preparation, distribution tables, institution lookup, and voice examples. No obvious gaps for the stated purpose.