Processa uma mensagem de texto de um cliente (WhatsApp/chat) usando IA para classificar intenção e gerar resposta automática. Intenções: boleto_2via, status_envio, saudacao, humano, duvida_fiscal, reclamacao.
| Name | Required | Description | Default |
|---|---|---|---|
| texto | Yes | Texto da mensagem recebida do cliente | |
| telefone | Yes | Telefone do cliente (formato: 5511999999999) | |
| whatsappMessageId | No | ID da mensagem WhatsApp (para rastreamento) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. It discloses that AI classifies intent and generates an automatic response, but it does not state side effects (e.g., whether the response is actually sent to the customer), what happens for the 'humano' intent (e.g., escalation), or any required permissions. This is a significant gap for a tool that triggers automatic actions.
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?
The description is a single, efficient sentence that packs a clear purpose and an enum-like list of intents. Every part is informative, though the intent list could arguably be part of the schema. No wasted words.
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?
The tool has no output schema, and the description does not explain what the tool returns or the format of the auto-response. It also lacks guidance on when to escalate to 'humano'. Given the action-oriented nature (generating and possibly sending responses), the description is not complete enough for an agent to understand the full impact and outcome.
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?
Schema description coverage is 100%, and each parameter has a description, so the schema already documents the parameters well. The description adds the intent taxonomy, which is useful but not directly tied to parameter syntax or additional meaning beyond what the schema provides. Baseline of 3 is appropriate.
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 uses a specific verb ('Processa') with a clear resource ('mensagem de texto de um cliente') and states the core function: 'usando IA para classificar intenção e gerar resposta automática'. It also lists concrete intent categories (boleto_2via, status_envio, etc.), which distinguishes it from sibling tools focused on financial operations.
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?
The description implies the tool is for processing incoming customer messages, but it does not provide explicit 'when to use' guidance or mention alternatives. Sibling tools like 'classificar_transacao' might overlap, but no exclusions are stated. The intent list gives context but no direct usage instructions.
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.
Many tools have distinct purposes, but several overlap: 'calcular_cbs_ibs' and 'consultar_aliquota_cbs_ibs' both deal with CBS/IBS rates, 'criar_cobranca' and 'criar_cobranca_pix' create similar things, and multiple metrics tools (dashboard_executivo, saude_financeira, autopilot_regua) could confuse an agent. The reconciliation_* group is well-differentiated, but overall the large, overlapping surface creates ambiguity.
Names mix Portuguese and English inconsistently (e.g., 'agendar_cobranca' vs. 'subscribe_webhook'). Most Portuguese names follow verb_noun, but many English names are noun_verb (e.g., 'reconciliation_execute') rather than verb_noun. Additionally, some names are vague or non-descriptive ('autopilot_regua', 'badges_contadores', 'metricas_escritorio'), breaking any predictable pattern.
61 tools is excessive for most MCP servers, even for a broad financial/fiscal automation domain. The count feels bloated, and several tools (e.g., criar_orcamento, listar_orcamentos) are dead weight being deactivated. This would likely be better split into multiple focused servers (e.g., cobranças, reconciliation, fiscal).
The tool surface covers many workflows: cobranças, NFS-e, reconciliation, tax simulation, dashboards, webhooks, and client insights. However, there are notable gaps in basic CRUD: no update/delete for cobranças or clientes, and no way to manage orcamentos (they're deactivated). The reconciliation module is very complete, but the overall surface has dead ends and missing lifecycle operations.