Skip to main content
Glama
JoseAlmeida-Ploomes

Ploomes MCP Server

guia_html_modelo_proposta

Retrieve HTML markup rules for Ploomes proposal templates to manually write form fields using and tags, eliminating the need for external LLM calls.

Instructions

    Retornar as regras de marcação de HTML de modelos de Proposta/Venda/
    Documento (PVD) do Ploomes, para que VOCÊ (o agente) escreva o HTML
    diretamente — sem chamar nenhum LLM externo nem o gateway de IA.

    POR QUE ESTA TOOL EXISTE: no Ploomes não há editor de campo de
    formulário separado do HTML. Os campos que aparecem no formulário de
    preenchimento são DERIVADOS pelo backend a partir do parsing do HTML
    do corpo do documento (Pages[].BodySourceCode). Ou seja, escrever o
    HTML com as tags certas é a única forma de "declarar" um campo. Esta
    tool entrega essas convenções (levantadas por engenharia reversa) em
    formato estruturado.

    SUBSTITUI gerar_modelo_html_llm (removida na consolidação de
    29/07/2026), que chamava a OpenRouter para pedir a um LLM externo o
    HTML que o agente desta conversa já sabe escrever — dependência
    quebrada (OpenRouterClient nunca existiu no repositório), custo e
    chave de API a mais, sem ganho. Se preferir o pipeline oficial da
    Ploomes, use gerar_modelo_html_ia (requer PLOOMES_AI_CLIENT_ID /
    PLOOMES_AI_CLIENT_SECRET).

    FLUXO RECOMENDADO (sem credencial de IA):
        1. guia_html_modelo_proposta  → estas regras.
        2. Você escreve o HTML, usando <field key="..."> para campos
           nativos e <newfield .../> onde precisar de campo customizado.
        3. criar_campos_novos_llm(novos_campos=[...])  → cria os campos
           customizados pela API normal do CRM e devolve as Keys.
        4. aplicar_campos_novos_html_llm(html, campos_criados)  → troca os
           <newfield> pelos <field key="..."> reais.
        5. salvar_modelo_proposta(corpo_html=html_final, ...)  → cria o
           modelo e a primeira página.
        6. montar_bloco_produtos_proposta(template_id=...)  → se precisar
           do bloco de itens (preferível a escrever a tabela na mão).

    ATALHO: para um modelo simples já com identidade visual do cliente,
    montar_modelo_proposta_com_identidade faz os passos 2/5/6 numa
    chamada — use esta tool aqui quando precisar de layout sob medida.

    Parâmetros:
        entidade_id: EntityId raiz do modelo (7=Proposta, 4=Venda,
            2=Negócio) — usado nos exemplos de entity_id dos newfield.
        incluir_bloco_produtos: se False, omite as regras do bloco
            repetível de produtos, deixando a resposta mais curta.
        formato: "markdown" devolve também uma versão em texto corrido das
            regras, útil para colar num prompt. Default: só estruturado.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
formatoNo
entidade_idNo
incluir_bloco_produtosNo
Behavior5/5

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

With no annotations, the description fully explains the tool's behavior: it returns structured rules derived from reverse engineering, does not call any external LLM, and is part of a recommended workflow. It discloses that it replaces a previous dependency (gerar_modelo_html_llm) and the rationale for removal. No contradictions or hidden behaviors.

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 long but well-structured with bold headers and clear sections (purpose, reason, fluxo, atalho, parameters). It front-loads the core purpose. However, it could be slightly more concise; for example, the historical context about the removed tool could be shortened.

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?

Given the complexity (HTML rules for proposal models), the description is complete: it explains the purpose, the problem it solves, the recommended workflow with 6 steps, a shortcut, and parameter details. No output schema exists, but the description doesn't need to explain return values since it's a guide returning rules.

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

Parameters5/5

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

Despite 0% schema description coverage, the description provides detailed explanations for all three parameters: entidade_id (EntityId root with examples), incluir_bloco_produtos (controls inclusion of product block rules), and formato (default vs markdown). This adds significant meaning beyond the raw 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 clearly states that the tool returns HTML markup rules for Ploomes proposal models (PVD), using a specific verb ('Retornar') and resource ('regras de marcação de HTML'). It distinguishes from siblings like gerar_modelo_html_ia and montar_modelo_proposta_com_identidade by explaining its unique role (providing rules, not generating HTML) and the context of replacing a removed tool.

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 when-to-use guidance via a 'FLUXO RECOMENDADO' (step 1) and an alternative shortcut (ATALHO) for simpler models. It also mentions when NOT to use this tool (if you want a simple model with visual identity) and names the alternative tool (montar_modelo_proposta_com_identidade). The purpose of the tool is contextualized with the problem it solves.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JoseAlmeida-Ploomes/ploomes-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server