Skip to main content
Glama

preparar_pesquisa

Prepara uma pesquisa de fan-out ISOLADO por persona (mede sem convergência). A PERGUNTA do usuário NÃO é enviada ao servidor (privacidade): você a classifica localmente pela 'fronteira' e a injeta você mesmo em cada pacote. Sorteia N personas e devolve UM pacote por persona (ficha + formato de resposta) + o protocolo para o HOST disparar UMA tarefa/subagente isolado por pacote — cada um responde só a SUA persona, sem ver as outras. A agregação é feita LOCALMENTE; o servidor não recebe nem armazena nenhuma resposta. Formatos: 'escolha' (opção única → distribuição), 'pontuar' (nota 0-10 por atributo → média+desvio por opção, recomendado para 'o que importa mais' e mais robusto a colapso), 'escala' e 'aberta'. Pode filtrar o segmento (classe, idade, região, etc.) pela DSL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nNoQuantas personas sortear (teto 30, para proteger a base e o custo de tokens do host).
seedNoOpcional. Por padrão o sorteio é ALEATÓRIO e o seed usado é devolvido no resultado — salve-o para reproduzir a MESMA amostra depois. Passe um número só se quiser repetir uma amostra específica.
filtroNoFiltro DSL do segmento — recorta por classe, idade, região, banco, dívida, etc. Ex.: "classe_social in ['Classe A'; 'Classe B'] & idade > 30 & se_investe == 'Sim'". Vazio = população toda.
opcoesNoOpções fechadas quando formato='escolha' ou 'pontuar'. Ex.: ['Versão A', 'Versão B']
formatoNoescolha=opção única fechada (gera distribuição, mas pode colapsar em amostra enviesada); pontuar=cada persona dá nota 0-10 a CADA opção (gera média+desvio por opção, preserva a preferência secundária — recomendado para 'o que importa mais'); escala=uma nota numérica; aberta=sem número, só temas/verbatim.escolha
escala_maxNoMáximo da escala quando formato='escala' (ex.: 5).
escala_minNoMínimo da escala quando formato='escala' (ex.: 1).

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations provided, the description fully discloses key behaviors: the user question is not sent to the server, aggregation is local, and the server does not store responses. It describes the workflow per persona. No contradictions.

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 a single, dense paragraph of about 250 words, front-loaded with the core action. It is efficient with no wasted sentences, though a more structured format could improve scanability.

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 complex tool without an output schema, the description covers what is returned (packets per persona and protocol for host), privacy, format behaviors, and filtering. It is sufficient for an agent to understand the tool's purpose and invocation.

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%, so baseline is 3. The description adds high-level context but does not provide additional per-parameter details beyond the schema's own descriptions. It explains the overall workflow but not new semantic constraints.

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 prepares a fan-out research per persona, with strong privacy guarantees and specific format options. It distinguishes from siblings like 'sortear_amostra' by emphasizing the isolated, privacy-preserving workflow.

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 explains when to use this tool (privacy-sensitive fan-out research) and provides guidance on selecting formats (recommending 'pontuar' for robustness). It does not explicitly list exclusions or alternative tools, but the context is clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation5/5

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.

Naming Consistency3/5

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.

Tool Count5/5

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.

Completeness5/5

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.