Arrumou Neural

Registrar mensagem enviada

send_guest_message

Registra no histórico da estadia uma mensagem entregue ao hóspede pelo canal informado (o Neural não possui envio automático de WhatsApp; o cliente MCP ou o usuário realiza a entrega). Exige aprovação com destinatário e conteúdo exatos.

Escopo: messages:send · Risco: external (prévia + aprovação do usuário obrigatória) · Efeitos: Cria MessageLog SENT e registra atividade. · INDISPONÍVEL nesta autorização (escopo não concedido ou papel sem o módulo)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "reservation_id": "<reservation_id>",
      "to": "<to>",
      "body": "<body>"
    },
    "name": "send_guest_message"
  }
}

Input Schema

Name	Required	Description	Default
`to`	Yes	Telefone do destinatário conforme devolvido pelo rascunho.
`body`	Yes
`channel`	No		WHATSAPP
`approval_id`	No	Id de uma aprovação já decidida pelo usuário para esta mesma ação. Omita para receber a prévia e o link de aprovação.
`template_name`	No
`reservation_id`	Yes
`idempotency_key`	No	Chave de idempotência escolhida pelo cliente; repetir a chave com os mesmos dados devolve o mesmo resultado.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by naming the concrete side effects (creates a MessageLog with SENT status and logs activity), the required scope (messages:send), the risk class (external, preview plus mandatory user approval), and current unavailability. The manual-delivery caveat is essential context an agent cannot get from readOnlyHint/destructiveHint alone, and nothing here contradicts those hints.

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?

Front-loaded with the core definition and the no-auto-send caveat, then a compact scope/risk/effects line and an availability note. Dense but every clause carries operational information; no filler.

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 7-parameter mutation with no output schema, the description covers the effects, approval flow, scope, and availability well. Minor gaps remain on the return payload of the preview call and on template_name, but an agent has enough to invoke it correctly.

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 only 43%, so the description must carry weight: it adds that approval is tied to the exact recipient and content and that the channel determines delivery path, which is meaningful beyond the schema. However, template_name and the reservation_id binding are never explained in the description, leaving part of the gap uncovered.

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?

States a precise verb+resource: it records a message already delivered to the guest in the stay history via the given channel, and explicitly clarifies that Neural does not auto-send WhatsApp — the client or user performs delivery. This distinguishes it clearly from sibling draft_guest_message and from list_guest_messages.

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?

Explicitly states the tool requires an approval bound to exact recipient and content, and that omitting approval_id returns a preview plus approval link, which tells the agent the correct call sequence. It also flags current unavailability under this authorization, preventing wasted calls. It stops short of naming draft_guest_message as the required precursor step.

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

All Arrumou Neural tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.