Skip to main content
Glama

Glacier length, mass and volume change (GLAMOS)

get_glacier_changes
Read-only

Retrieve measured length, mass-balance, and volume changes for a Swiss glacier by name or SGI ID, including survey intervals, cumulative retreat, and mean thickness change.

Instructions

Measured changes of one Swiss glacier: front variation per survey interval (m) with cumulative retreat, annual/winter/summer mass balance (mm water equivalent) with ELA, and geodetic volume change (km³, mean thickness change). Give a name or SGI id. Example: {glacier: 'Rhonegletscher'}, {glacier: 'B43-03', series: 'length'}.

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": {
      "glacier": "<glacier>"
    },
    "name": "get_glacier_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
lastNoMost recent N observations per series
seriesNoall
glacierYesGlacier name (or part) or SGI id from list_glaciers

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description goes further by disclosing the exact data payloads per series, their units, and derived fields such as cumulative retreat and mean thickness change. It omits notable behavioral facts like the default truncation to the 20 most recent observations per series and any handling of missing records, keeping it short of a 5.

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 front-loaded: series/units first, then identifier guidance, then compact examples. It is dense but every clause carries information; a slightly clearer separation between return content and input instructions would improve it.

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

Completeness3/5

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

With no output schema, the description does the heavy lifting by describing return fields and units, which is appropriate. But for a multi-series retrieval tool it leaves gaps: the default 20-observation cap, temporal coverage of the measurements, and behavior for an unmatched glacier name are all undisclosed.

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 coverage is 67%, so the schema already documents the glacier and last parameters. The description adds real meaning for series by naming the three data families and demonstrating a series filter, but it does not explicitly restate the allowed series values or explain how the default 'all' combines them, nor does it mention the last-N truncation.

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?

The description names a specific resource (changes of one Swiss glacier) and enumerates exactly what is returned: front variation per survey interval in metres with cumulative retreat, annual/winter/summer mass balance in mm w.e. with ELA, and geodetic volume change in km³ with mean thickness change. Units and series names make it unmistakable what the tool does and how it differs from generic measurement tools.

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 says to supply a name or SGI id and supplies two worked invocation examples ({glacier:'Rhonegletscher'} and a series-filtered one), which is useful input guidance. However, there is no explicit when-to-use or when-not-to-use statement, and no forward pointer to list_glaciers for identifier discovery (that only appears in the schema).

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