Skip to main content
Glama

buscar_samd_recentes

Find recently registered Class III/IV medical devices in Anvisa and identify which likely use AI/ML, with confidence and justification. Filter by AI or software to focus on SaMD candidates.

Instructions

Lista dispositivos médicos Classe III/IV registrados recentemente na Anvisa.

Para cada registro, classifica se o produto usa IA ou aprendizado de máquina. A Anvisa não publica esse campo: a classificação é heurística, feita por um LLM local lendo o texto do registro, e cada item traz confiança e justificativa. Não apresente o veredito como fato regulatório.

Args: dias: tamanho da janela, em dias, a contar de hoje. apenas_com_ia: quando True, devolve só os classificados como usando IA. apenas_software: quando True, analisa só registros cujo texto sugere software. SaMD é raro no registro (13 de 1.832 registros Classe III/IV do último ano mencionam software), então sem esse filtro a busca gasta as chamadas de LLM em cânulas e parafusos. Desligue para varrer tudo, ao custo de ser lento.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
diasNo
apenas_com_iaNo
apenas_softwareNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
diasYes
avisoNo
fonteYes'mock' = dado de exemplo, ainda não é registro real da Anvisa
totalYes
resultadosYes
apenas_com_iaYes
indeterminadosNoQuantos registros ficaram de fora por terem sido classificados como sem IA com confiança baixa — ou seja, o texto não permitiu decidir, o que não é o mesmo que não usar IA

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility and delivers thoroughly. It discloses the classification is heuristic, performed by a local LLM, and includes confidence and justification per item. It explicitly warns against presenting the verdict as regulatory fact, and notes the cost and speed implications of disabling the filter. This goes well beyond a simple read-only hint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured with a clear purpose statement, a behavioral note, and an Args section. It is slightly longer than minimal but every sentence adds value—no fluff. The key caveat about heuristic classification is front-loaded, and the filter explanation is concise yet informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, heuristic nature, cost trade-offs, and parameter semantics. It mentions output includes confidence and justification, and an output schema exists to define the full return format. Minor gaps like pagination or error handling are not addressed, but given the output schema and the richness of the description, it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain each parameter, and it does. The Args section clarifies 'dias' as a window from today, 'apenas_com_ia' as a filter, and 'apenas_software' with additional rationale about rarity and cost. Defaults are not restated, but the schema provides them; the description adds meaningful semantics beyond names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists Class III/IV medical devices recently registered with Anvisa and classifies each for AI/ML usage. The verb 'Lista' and resource 'dispositivos médicos Classe III/IV' are specific, and the added classification step is explicit. It clearly distinguishes itself from the sibling tool about medication status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides strong contextual guidance on when to use the 'apenas_software' filter, explaining the rarity of SaMD and the cost of LLM calls when not filtering. It implies the tool is for AI-related medical device discovery, though it doesn't explicitly contrast with the sibling tool (which is unrelated). The trade-off guidance for filters is a clear usage instruction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.