Agrega achados por prestador e mês, sem expor dados das guias; CPF é pseudonimizado. Quando usar: para analisar rejeições por prestador. Quando não usar: para consultar guias individuais ou corrigir lotes.
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| lotes | Yes | ||
| regras | No | ||
| contexto | No | ||
| operadora | No | ||
| segredo_pseudonimo | No |
| Name | Required | Description | Default |
|---|---|---|---|
| guias | Yes | ||
| lotes | Yes | ||
| linhas | Yes | ||
| versao | Yes | ||
| ignorados | Yes | ||
| prestadores | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses aggregation and privacy behavior (no raw guide data exposed, CPF pseudonymized), which is materially useful. It does not state read-only status, side effects, or performance/rate limits, so it is not fully transparent.
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?
Two compact sentences with the aggregation behavior front-loaded, followed by explicit use/non-use routing. No filler, and both clauses earn their place.
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?
Purpose and routing are clear, and the output schema covers return values. However, for a tool with six parameters, nested objects, and zero schema descriptions, the definition leaves the agent without guidance on populating 'lotes', 'data', 'operadora', 'contexto', or 'regras'.
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 0% for six parameters, including the required 'lotes' array and nested 'contexto'/'regras' objects. The description only hints at pseudonymization (likely 'segredo_pseudonimo') and does not explain 'data', 'operadora', 'lotes' format, or when 'contexto'/'regras' are needed, so it fails to compensate for the coverage gap.
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?
States a specific verb and resource ('Agrega achados por prestador e mês') plus scope constraints ('sem expor dados das guias', pseudonymized CPF) and explicitly excludes individual guide lookup and batch correction. An agent can distinguish it from siblings like tiss_apply_fixes or parsing tools without opening the schema.
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?
Includes explicit 'Quando usar' and 'Quando não usar' clauses that route rejection analysis here and individual guide queries / batch corrections elsewhere. It does not name the competing sibling tools directly, so routing is clear by task but not by exact tool name.
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.