Skip to main content
Glama
JoseAlmeida-Ploomes

Ploomes MCP Server

gerar_modelo_html_ia

Create and modify HTML document templates for proposals and sales using natural language prompts. Optionally supply reference files or previous HTML to guide the AI in generating the layout.

Instructions

    Gerar (ou editar) o HTML de um modelo de Proposta/Venda/Documento (PVD)
    usando a feature de IA do Ploomes ("Gerador HTML com IA").

    Endpoint: POST {PLOOMES_AI_BASE_URL}/generate_document_template
    (documentado em handoff-gerador-html-ia.pdf). Requer as variáveis de
    ambiente PLOOMES_AI_CLIENT_ID e PLOOMES_AI_CLIENT_SECRET — credenciais
    próprias desta feature de IA, diferentes da User-Key do CRM.

    Parâmetros:
        root_entity_id: Id da entidade raiz do modelo (ex.: Id de uma
            Proposta/Venda existente) — usado pela IA para calcular o
            caminho (path) dos campos que ela detectar/sugerir.
        prompt: instrução em linguagem natural descrevendo o layout
            desejado ou a alteração a ser feita. Obrigatório se não houver
            anexos.
        previous_html: HTML atual da sessão — informe ao EDITAR um modelo
            já gerado (a IA usa como base e aplica só o que foi pedido).
            Deixe vazio para gerar do zero.
        anexos: lista de arquivos de referência (PDF, Word, PNG, JPEG),
            cada item como {"filename": "...", "content_base64": "...",
            "mime_type": "application/pdf"}. Obrigatório se não houver
            prompt.
        idioma: idioma do usuário (ex.: "pt-BR").

    Observações (da documentação original):
        1. Ausência de previous_html sinaliza geração do zero; presença
           sinaliza edição.
        2. A IA não tem memória de conversa — cada chamada de edição leva
           em conta apenas o previous_html enviado, não o histórico.
        3. Não importa imagens como assets finais — se o anexo contém
           imagens, o HTML gerado usa um bloco placeholder; a imagem
           definitiva precisa ser configurada manualmente depois.
        4. Depois de gerar, use identificar_campos_html_ia (opcional) para
           detectar e criar os campos dinâmicos automaticamente, ou insira
           o HTML direto em salvar_modelo_proposta / montar_bloco_produtos_proposta.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
anexosNo
idiomaNopt-BR
promptNo
previous_htmlNo
root_entity_idYes
Behavior5/5

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

No annotations provided, so description fully bears transparency. Discloses no conversation memory, image placeholder behavior, credential requirements, and the role of previous_html. Leverages observations to explain limitations and side effects.

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?

Well-structured with paragraphs, bullet points, and numbered observations. Front-loads purpose and endpoint. Some redundancy (parameter list repeated in observations), but overall clear and appropriately sized for complexity.

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?

Covers input thoroughly, mentions follow-up tools, and addresses edge cases (placeholder images). No output schema, so description could explicitly state return value (HTML string) but doesn't. Still, context is largely complete.

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?

Schema has 0% description coverage, so description must compensate. It provides detailed explanations for all 5 parameters, including example values, optionality constraints (prompt vs anexos), and data types for anexos. Adds significant meaning beyond 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?

Description clearly states purpose: generate or edit HTML of Proposta/Venda/Documento model using AI feature. It specifies endpoint, credentials, and distinguishes between generation and editing based on previous_html parameter.

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?

Provides explicit usage context: when to generate vs edit, requirements (prompt or anexos), and recommends follow-up tools. Lacks explicit 'when not to use' but clearly differentiates from manual template methods.

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