Vigia uma compra (precisa do token edm_…): fotografa agora e registra eventos de retificação, documento novo, suspensão, prazo adiado e valor, mais avisos de prazo. A primeira é grátis; as seguintes custam até 30 dias após o encerramento.
| Name | Required | Description | Default |
|---|---|---|---|
| canal | No | pull, webhook ou email (padrão pull) | pull |
| destino | No | URL https (webhook) ou e-mail (email) | |
| compra_id | Yes | id da compra (vem da busca) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / canal / defaultAdded value: +"pull"Input schema / properties / canal / enumAdded value: +[
+ "pull",
+ "webhook",
+ "email"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool 'fotografa agora' and 'registra eventos', which implies a state-changing side effect, and it mentions the cost implications for subsequent calls. It does not specify whether the tool is idempotent, what exactly happens after the first call, or what the response contains, but it gives enough behavioral context for a basic user.
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, compact sentence that packs multiple relevant details: the action, the required token, the event types tracked, and the pricing model. There is no redundant or filler wording, making it efficient and well-structured.
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 description provides essential context like the token requirement, the events tracked, and the cost structure, which is useful for deciding to call the tool. However, it does not mention return values or how this tool relates to the sibling 'vigia_eventos' and 'alertas_compras' tools, leaving some contextual gaps for a fully informed call.
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?
All three parameters are described in the schema: canal is an enum with clear options, destino is explained as either an HTTPS URL or an email address, and compra_id is identified as the purchase ID from a search. The descriptions are minimal and do not clarify edge cases such as whether destino is required when canal is 'pull', but they cover the basic meaning of each parameter.
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 clearly states the tool's purpose: 'Vigia uma compra' and explains that it captures a snapshot and registers events such as rectification, new documents, suspension, deadline changes, and value changes. It also distinguishes itself by mentioning the required edm_ token and the pricing model, which helps clarify its role among the sibling tools.
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 includes practical usage information such as the need for the edm_ token and the free-first-then-paid cost model, which guides when it is appropriate to call. However, it does not explicitly contrast this tool with siblings like 'vigia_eventos' or 'alertas_compras', so the when-to-use guidance is not fully explicit.
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.
Most tools target a distinct resource and action, and descriptions clearly separate alerta_por_cnpj from criar_alerta and vigiar_compra from vigia_eventos. Only recibo is somewhat generic without reading its description, and the two alert-creation tools share a conceptual overlap.
All names use snake_case, but conventions vary widely: some are verb+noun (criar_alerta, buscar_licitacao), some noun+verb (credito_recarregar), many are noun+noun (credito_saldo, alertas_compras, vigia_eventos), and health/api_index are English amid Portuguese names. The set feels less predictable than it could be.
With 19 tools, the server covers several subdomains: search, documents, alerts, watches, billing, and account management. It is a bit heavy and includes optional meta endpoints like api_index and health, but the count is justifiable for the scope.
The surface covers search, purchase details, document extraction, alert creation and matches, watch creation/events, credits, and webhook management. However, there is no way to list, update, or cancel existing alerts or watches, which is a notable lifecycle gap.