Busca empresas (q e/ou filtros f=JSON).
| Name | Required | Description | Default |
|---|---|---|---|
| f | No | JSON string de filtros | |
| q | No | Termo de busca, entre 2 e 120 caracteres. | |
| uf | No | Restringe a uma unidade da federação. | |
| page | No | Página, começando em 0. | |
| pageSize | No | Resultados por página, de 1 a 50. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / page / defaultAdded value: +0Input schema / properties / page / descriptionAdded value: +"Página, começando em 0."Input schema / properties / pageSize / defaultAdded value: +20Input schema / properties / pageSize / descriptionAdded value: +"Resultados por página, de 1 a 50."Input schema / properties / q / descriptionAdded value: +"Termo de busca, entre 2 e 120 caracteres."Input schema / properties / uf / descriptionAdded value: +"Restringe a uma unidade da federação."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action of searching companies, without mentioning read-only nature, pagination, response format, or any side effects. This is insufficient for a search tool with 5 parameters.
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, short sentence that front-loads the action ('Busca empresas') and immediately mentions the main parameters. There is no wasted wording, and the structure is optimally concise.
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?
With 5 parameters, no output schema, and no annotations, the description is far too brief. It fails to explain pagination usage, response structure, or any practical details needed for correct invocation. The agent is left without context on how to handle results or edge cases.
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%, with each parameter already described. The description adds a small note that q and/or filters (f=JSON) can be used, which is a minor clarification beyond the schema. However, it does not explain syntax or how parameters interact, so it remains at the 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?
Description clearly states 'Busca empresas' (search companies), specifying the verb and resource. It also mentions the key parameters q and f, but does not distinguish this from sibling tools like suggest or get_cnpj, leaving some ambiguity in tool selection.
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?
No guidance is provided on when to use this tool versus siblings. There is no mention of exclusions, prerequisites, or conditions that would steer an agent toward or away from this tool. The description only states what it does, not when to use it.
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.
Each tool targets a clearly distinct purpose: exact CNPJ lookup, company search, autocomplete, AI filter generation, idea evaluation, reference data, session/watches management, and API utility endpoints. There is no meaningful overlap that would cause an agent to select the wrong tool.
The naming is inconsistent: some tools use verb_noun snake_case (get_cnpj, add_watch, list_watches), some are bare English verbs (search, suggest, contact), and some are bare nouns or abbreviations (health, local, ref, api_index). It also mixes languages, with Portuguese avaliar alongside English names.
13 tools is within a reasonable range for a server covering CNPJ lookup, search, evaluation, monitoring, and API metadata. The count feels slightly broad because several utility endpoints (health, api_index, contact, local) are auxiliary, but no tool is redundant.
The core lookup, search, evaluation, and reference workflows are covered well. However, the monitoring lifecycle is incomplete: add_watch and list_watches exist but there is no remove_watch, and monitor_session has no session status or termination counterpart, creating a dead end for the watch flow.