Skip to main content
Glama

SNB cube time series

get_snb_data
Read-only

Fetch labelled Swiss National Bank time series for a data cube, including dimension labels, units, scale and recent values, with optional date ranges and dimension filters to target specific series.

Instructions

Fetch labelled time series from any Swiss National Bank data-portal cube: each series has its dimension labels, unit, scale and the most recent values (trimmed to values_per_series). Optional date range (YYYY, YYYY-MM or YYYY-MM-DD matching the cube frequency) and dimension_selection from get_snb_cube_dimensions, e.g. {"D0":["M0"],"D1":["EUR1","USD1"]}. Examples: cube_id='zimoma' (money market rates incl. SARON), cube_id='devkum', from_date='2024-01'.

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": {
      "cube_id": "<cube_id>"
    },
    "name": "get_snb_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax series returned (default 20)
cube_idYesSNB cube id, e.g. 'devkum' (monthly FX), 'zimoma' (money market rates); see list_snb_datasets
to_dateNoEnd date, same format as from_date
languageNoLabel language: en or de (default en)en
from_dateNoStart date, e.g. '2020-01' (monthly) or '2024-06-01' (daily)
values_per_seriesNoMost recent observations kept per series (default 24; trimmed further if the output would exceed the 50 KB response cap)
dimension_selectionNoDimension id → item ids, e.g. {"D0":["M0"],"D1":["EUR1"]}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover read-only and open-world status, yet the description still adds real value: it discloses that dates must match the cube frequency, that values_per_series is trimmed further under a 50 KB response cap, and what each series carries. It does not discuss failure modes for invalid cube ids or dimension ids.

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?

Front-loaded with the core action and return shape, then parameters and examples. Dense but nearly every clause carries information; the inline examples are justified by the awkward dimension-map format.

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 7 parameters, a nested object and no output schema, the description adequately explains return structure and truncation behavior. Minor gaps remain around what happens on an invalid cube or dimension selection, but nothing essential to a correct call is missing.

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 100% (baseline 3), and the description still adds meaning: the YYYY/YYYY-MM/YYYY-MM-DD options are tied to cube frequency, dimension_selection is shown as a concrete map {"D0":["M0"],"D1":["EUR1","USD1"]}, and cube_id values are exemplified.

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?

States a specific verb and resource ('Fetch labelled time series from any Swiss National Bank data-portal cube') and immediately describes what each returned series contains (dimension labels, unit, scale, recent values), so it is clearly distinguishable from metadata-oriented siblings like get_snb_cube_dimensions or list_snb_datasets.

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 concrete routing context: dimension_selection comes from get_snb_cube_dimensions and cube ids are illustrated with 'zimoma' and 'devkum' (schema points to list_snb_datasets). It never states when not to use it versus query_data_cube or describe_data_cube, so the guidance is strong but not exhaustive.

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

Deploy Server

Other Tools