Skip to main content
Glama

What changed: impulse log of the sensors

get_changes
Read-only

Free. Instead of polling every sensor, ask what changed since a time: new gas storage day, new BaFin measure, new significant earthquake, change of the active flood warnings, change of a NOAA space-weather scale. Each event has detected_at (when our poll noticed it, at most about 6 minutes after the source published) and the source time where there is one. Facts, not predictions. The log starts after its baseline_at and keeps the latest 100 events. Sensor HTTP endpoints also answer 304 to If-None-Match.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sinceNoISO time (2026-11-11T10:00:00Z) or epoch seconds/milliseconds
sensorNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses freshness (detected_at lag of at most ~6 minutes), retention (latest 100 events, starting after baseline_at), and that both detection time and source time are provided. It also frames the data as 'Facts, not predictions,' which sets expectations about content. This is meaningful operational context the annotations cannot convey.

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 delta-feed rationale is front-loaded and each sentence carries useful information (freshness, retention, conditional requests). 'Free.' is throwaway marketing framing, and the run-on list of event types is dense but still readable.

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 no output schema, the description does describe the returned event shape (detected_at plus source time) and the log's retention boundary, which is the critical missing piece for a delta tool. It does not spell out the full per-event payload or a default for limit, leaving a small gap.

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 description coverage is only 33%, so the description must compensate: it explains that 'since' is a time cursor, that the log is a change feed rather than a full dump, and it names the five sensor domains matching the enum. The 'limit' parameter is only implied via the 100-event cap rather than explained as a caller-controlled count.

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 concrete verb and resource: 'ask what changed since a time' over a sensor impulse log, and enumerates the event types (gas storage, BaFin, flood warnings, earthquakes, space-weather scales). It also distinguishes itself from the polling alternative ('Instead of polling every sensor'), though it does not address the near-identical sibling get_changes_since, leaving some ambiguity.

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?

It gives a clear when-to-use rule: use this delta feed rather than polling each sensor endpoint, and notes the HTTP 304/If-None-Match path for conditional requests. It stops short of stating when not to use it or how it differs from get_changes_since.

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.