Skip to main content
Glama
bcb-mcp
by msperlin

Get Series

get_series
Read-only

Download Brazilian Central Bank SGS time series by ID or English/Portuguese alias, with parquet caching, automatic chunking, and per-series failure reporting.

Instructions

Download BCB-SGS time series (the analogue of GetBCBData::gbcbd_get_series).

Long spans are split into API-friendly chunks automatically, results are cached as parquet files, and only missing date ranges are downloaded on subsequent calls. Failed ids are reported in failures instead of aborting the whole request, exactly like the R package.

Rows are compact: each one has ref_date, value and series_id. The name, unit, frequency and source of every series are in the series array, so pair rows with series before writing prose (units differ across ids).

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": {
      "series_ids": "<series_ids>"
    },
    "name": "get_series"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_rowsNoMaximum observations kept per series (most recent are kept). Defaults to 1000; raise it only when you really need the full history.
last_dateNoEnd date (YYYY-MM-DD or DD/MM/YYYY). Defaults to today.
use_cacheNoReuse locally cached parquet data and download only missing date ranges. Set to false to force a fresh download.
first_dateNoStart date (YYYY-MM-DD or DD/MM/YYYY). Defaults to five years before last_date.
series_idsYesSGS series identifiers. Each item may be a numeric SGS id (11) or a dictionary alias in English/Portuguese ('selic', 'ipca', 'desemprego', 'dolar'). Use search_series() when unsure.
format_dataNo'long' (default) returns one row per observation with series_id/series_name columns; 'wide' pivots to one column per series.long
series_namesNoOptional display names, positionally aligned with series_ids (like naming a vector in R's GetBCBData).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / max_rows / default
      Previous value: -5000New value: +1000
    • changedInput schema / properties / max_rows / description
      Previous value: -"Maximum observations kept per series (most recent are kept). Defaults to 5000."New value: +"Maximum observations kept per series (most recent are kept). Defaults to 1000; raise it only when you really need the full history."
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses automatic chunking of long spans, parquet caching with incremental download of only missing ranges, and most importantly that failed ids are returned in `failures` rather than aborting the whole call. That partial-failure contract is the kind of behavior an agent cannot get from structured fields and would otherwise have to discover by trial.

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?

Four short paragraphs, front-loaded with what the tool does, then behavior, then return shape. Most sentences earn their place; the explicit R-package comparison ('exactly like the R package') is mildly redundant for an agent without that context but clarifies failure semantics.

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?

With a full schema and an output schema present, the description covers the remaining gaps an agent needs: chunking, caching, partial failure reporting, and a warning to join series metadata before interpreting values. Only external concerns such as rate limits or API/auth prerequisites are unaddressed.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents every parameter including aliases, date formats, and format_data modes. The description adds contextual meaning about the output shape (compact rows plus a `series` metadata array, units differing across ids) but does little to deepen parameter semantics beyond the schema baseline.

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 verb and resource ('Download BCB-SGS time series') and anchors it to a known analogue (GetBCBData::gbcbd_get_series), so the agent knows exactly what comes back. It does not explicitly distinguish itself from siblings like get_series_stats or describe_series, leaving that differentiation to inference.

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?

Usage is implied through behavioral notes: caching makes repeated calls cheap, and the recommendation to pair rows with `series` before writing prose implies a data-retrieval-then-analyze workflow. There is no explicit when-to-use/when-not versus the sibling stats/describe/list tools; the pointer to search_series appears only inside the schema, not the description.

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