Skip to main content
Glama

OBM - Open Brazil Market

Série de preço ou cota

obm_get_price_history
Read-onlyIdempotent

Série diária de preço, cota ou pontos do índice. Bonds: PU sem arredondamento; bid é mercado comprador (Tesouro: Taxa Venda), ask é mercado vendedor (Tesouro: Taxa Compra); sem datas, última cotação; start/end até 366 dias inclusivos, sem paginação, ordem decrescente. Cite source e reference_date, nunca hoje se a referência for anterior. Demais classes: padrão 12 meses; até 100 linhas por página, em ordem cronológica. Use start e end para estreitar ou page para continuar.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "asset_type": "<asset_type>",
      "identifier": "<identifier>"
    },
    "name": "obm_get_price_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoFim (AAAA-MM-DD). Padrão: o dado mais recente.
pageNoPágina; continue daqui se houver mais.
startNoInício (AAAA-MM-DD). Padrão: 12 meses; bonds sem start/end devolve só a última cotação.
page_sizeNoLinhas por página (máximo 100).
asset_typeYes
identifierYesTicker, CNPJ ou código do título; Tesouro pode conter espaço, como NTN-B PRINCIPAL_2035-05-15.

Output Schema

NameRequiredDescriptionDefault
dataYes
metaYes
sourceYes
reference_dateYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: bond PU without rounding, bid/ask mapped to Tesouro Taxa Venda/Compra, a 366-day inclusive limit with no pagination and descending order for bonds, versus 12-month default and chronological paging for other classes. It also adds citation guidance. Missing only error and empty-result behavior.

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 content is dense and front-loaded: first sentence defines the series, then class-specific semantics, then parameter guidance. It is somewhat run-on with heavy semicolon chaining, but nearly every clause carries operationally relevant information.

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?

For a multi-class time-series tool with six parameters, pagination differences, and an existing output schema, the description supplies the missing per-class defaults, ordering rules, and limit constraints an agent needs to call it correctly. Return-format details are appropriately left to the output schema.

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

Parameters4/5

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

Schema coverage is already high (83%), but the description adds semantics the schema does not: the 366-day inclusive ceiling for bonding queries, the 'last quote only' fallback when dates are omitted, and the differing ordering and pagination behavior by asset class. These details materially affect how start, end, and page should be set.

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?

The description states a specific resource and output shape ('Série diária de preço, cota ou pontos do índice') with the asset classes it covers. It is clearly a time-series retrieval tool, distinguishable from snapshot-style siblings such as obm_get_asset, though no sibling is named.

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

Usage Guidelines3/5

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

It gives concrete usage rules — use start/end to narrow, page to continue, and bonds without dates return only the last quote. There is no explicit when-not-to-use or routing to a sibling tool, so guidance is useful but not complete.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources