Skip to main content
Glama

Dados B3

by io.github.Val7h
OverviewDiscussionsAdmin

precos

Série DIÁRIA de preços de uma AÇÃO numa chamada só (abertura, máxima, mínima, fechamento, médio, volume, quantidade, negócios), do COTAHIST da B3, do mais antigo ao mais recente. de/ate em AAAA-MM-DD recortam; limite (padrão 1500, máximo 20000) corta a partir do mais antigo e avisa.

O preço NÃO é ajustado: os eventos societários do período vêm junto (eventos) para quem monta o retorno total. WEGE3 gratuita; demais tickers SEM chave devolvem uma AMOSTRA (últimos 30 pregões) com um aviso que diz como ter a série inteira (chave grátis em chave_api) e que desempenho responde sem chave; com chave, a série completa.

★ FORMATO COMPACTO (04/10/2026). Cinco anos de série completa pesam ~250 KB, mais do que cabe no contexto de um cliente de IA (o ChatGPT recebeu os 1.248 pregões e não conseguiu processá-los). Por padrão a resposta traz só data,fechamento em forma de colunas (colunas + linhas, ~28 KB). Peça mais com campos (lista separada por vírgula entre data, ticker, abertura, maxima, minima, fechamento, medio, volume, quantidade, negocios) ou campos="todos" para a lista completa de objetos em serie.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deNo
ateNo
camposNodata,fechamento
limiteNo
tickerYes
chave_apiNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / campos
      Added value: +{
+  "default": "data,fechamento",
+  "title": "Campos",
+  "type": "string"
+}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden. It discloses non-adjusted prices, accompanying corporate events, free access for WEGE3, sample fallback (last 30 pregões) with warning, API-key path for full series, default compact response format, and the limit cap (1500 default, 20000 max) that cuts from the oldest and warns.

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 front-loaded with purpose and key constraints, and is generally well structured. It is longer than strictly necessary: the ChatGPT anecdote and repeated format explanation add weight, though they do serve the compact-format rationale.

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

Completeness5/5

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

Given 6 parameters, no annotations, no output schema, and many sibling tools, the description is complete enough for correct invocation. It covers purpose, authentication and sample behavior, output shape (`colunas`/`linhas` vs `serie`), and parameter formats.

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 description coverage is 0%, so the description must compensate. It documents `de`/`ate` in AAAA-MM-DD, `limite` default/max behavior, `campos` allowed values and 'todos', and the authentication semantics of `chave_api`. Only `ticker` is left implicit, which is obvious from the tool name.

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

Purpose4/5

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

States a specific resource: daily price series for one stock from COTAHIST B3, oldest to newest, and enumerates the returned price fields. The purpose is unmistakable, but it does not explicitly contrast itself with sibling tools such as `hoje` or `eventos`, so sibling differentiation is only partial.

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?

Gives clear context for date filters and limits, and notes that `desempenho` works without a key while `precos` can return a sample without one. However, it never states when to choose `precos` over other price-related siblings, so usage is implied rather than explicitly routed.

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

All Dados B3 toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources