A lista de CNAE como o alerta por CNPJ a lê: descrição oficial (IBGE), família e termos do dicionário e fornecedores ativos no SICAF. Sem q, o ranking de quem mais vende para o governo. Grátis.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Prefixo do código (1412) ou palavra da descrição (opcional) | |
| limite | No | 1 a 100 (padrão 20) |
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?
With no annotations, the description carries the burden of behavioral disclosure. It partially does so by describing output components and the q/no-q behavior. Still, it does not state whether the operation is read-only, what the response shape is, or any error/edge-case behavior, and the garbled phrasing obscures the intended behavior.
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 very short but poorly structured as a run-on, with the confusing opening 'A lista de CNAE como o alerta por CNPJ a lê' preceding the more informative content. It is not clearly front-loaded and would be clearer as separate sentences.
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?
Given no output schema and no annotations, the description should provide a complete picture. It does mention key return fields and the ranking behavior, but it lacks a clear statement of the response type (list vs ranking) and the relationship with CNPJ alerts. This leaves some ambiguity for an agent deciding how to invoke it.
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 coverage is 100%, so the schema already documents q and limite well. The description adds meaningful semantics by explaining the effect of omitting q (ranking instead of filtered list) and explicitly ties q to code prefix or description word, going beyond the schema baseline.
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 identifies the resource as 'A lista de CNAE' and enumerates its contents (official IBGE description, family, dictionary terms, active SICAF suppliers), so an agent can grasp the basic purpose. However, the phrase 'como o alerta por CNPJ a lê' is vague and there is no clear verb or explicit differentiation from the sibling alert 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 provides conditional behavior: 'Sem q, o ranking de quem mais vende para o governo' indicates that omitting q changes the result to a ranking. But it gives no guidance on when to use this tool versus the sibling alert/CNPJ tools, nor any exclusion criteria.
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.