Skip to main content
Glama

Read and query a CSV/JSON data file from data.geo.admin.ch

read_geodata_asset
Read-only

Fetch and query CSV or JSON assets from data.geo.admin.ch, returning rows you can filter, sort and page, with tail support for recent time-series values.

Instructions

Download a CSV or JSON asset from data.geo.admin.ch (href from get_geodata_collection_items) and return it as rows you can filter, sort and page, e.g. MeteoSwiss SwissMetNet station files. Filters: where={column: value} (exact), '~text' (substring), '>n'/'<n' (numeric). tail=true returns the latest rows of a time series. Example: url='https://data.geo.admin.ch/ch.meteoschweiz.ogd-smn/ber/ogd-smn_ber_d_recent.csv', tail=true, limit=7, columns=['reference_timestamp','tre200d0','rre150d0']. Large historical files may exceed max_mb, prefer '_recent' or '_now' files.

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": {
      "url": "<url>"
    },
    "name": "read_geodata_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAsset href on https://data.geo.admin.ch/ (CSV, TXT or JSON/GeoJSON)
sortNoSort column; prefix '-' for descending
tailNoReturn the LAST matching rows (latest values of a time series)
limitNoMax rows (default 50)
whereNoColumn filters, e.g. {"station_abbr": "BER"} or {"tre200d0": ">25"}
max_mbNoDownload size cap in MB (default 8, max 20)
offsetNoSkip this many matching rows (ignored with tail)
searchNoCase-insensitive text search across all columns
columnsNoColumns to return (default all; max 40)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: a download size ceiling enforced by max_mb and the failure risk on large historical files, plus that tail returns the latest rows of a time series. It does not say what happens when the cap is exceeded (error vs truncation), which is the remaining gap.

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

Conciseness5/5

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

Front-loaded with the action and return shape, then filters, then tail, then a concrete example, then a caveat. Every sentence carries distinct information and nothing is repeated from the schema verbatim.

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?

For a 9-parameter read-only fetch tool with no output schema, the description covers provenance, filtering, paging, tail behavior, column selection and size limits. Minor omissions remain around the row object structure and the exact behavior when max_mb is exceeded, but an agent could call this correctly from what is given.

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%, so baseline would be 3, but the description contributes real operator semantics not spelled out in the schema: '~text' for substring matching and '>n'/'<n' for numeric comparison in where, and tail semantics tied to time-series recency. The worked example also shows how columns, tail and limit compose on a real SwissMetNet file.

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 ('Download a CSV or JSON asset from data.geo.admin.ch') and goes further by describing the return shape ('rows you can filter, sort and page'), which no sibling implies. It also anchors the input to its producer ('href from get_geodata_collection_items'), so the agent knows exactly where the URL comes from.

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?

Clear context for when to reach for this tool (fetching an asset href obtained from get_geodata_collection_items) plus concrete avoidance guidance: prefer '_recent' or '_now' files when historical files may exceed max_mb. It stops short of naming a sibling alternative for large historical data, but the conditional advice is actionable.

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