tibber-mcp-server

Find Cheapest Hours

find_cheapest_hours

Identify the cheapest electricity hours for high-consumption devices. Set runtime, resolution (hourly/quarter-hourly), and window to get optimal start times for cost savings.

Instructions

Findet die günstigsten Stunden für einen Verbraucher (Waschmaschine, Spülmaschine, E-Auto-Ladung).

duration_hours: Laufzeit des Verbrauchers in Stunden, Bruchteile erlaubt (1.5 = 90 min). Wird auf ganze Rasterintervalle aufgerundet. resolution: 'HOURLY' oder 'QUARTER_HOURLY' — im Viertelstundenraster findet es kurze Preissenken und plant Laufzeiten auf 15 min genau. window: 'today', 'tomorrow' oder 'next_24h'. contiguous: True = zusammenhängender Block, False = billigste Einzelstunden. next_24h schließt das laufende Intervall ein — start_hours[0] kann in der Vergangenheit liegen (sofort starten).

Input Schema

TableJSON Schema

Name	Required	Default
`window`	No	next_24h
`home_id`	No
`contiguous`	No
`resolution`	No	HOURLY
`duration_hours`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.0Sep 26, 2026
- changedInput schema / properties / duration_hours / type
```
Previous value: -"integer"New value: +"number"
```
- addedInput schema / properties / resolution
```
Added value: +{
+  "default": "HOURLY",
+  "type": "string"
+}
```
First observedv0.1.0Jul 29, 2026

TDQS

A4.1/5.0

Behavior5/5

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

With no annotations, the description carries all behavioral disclosure and does it well: it explains rounding to grid intervals, the effect of HOURLY vs QUARTER_HOURLY, contiguous vs cheapest individual hours, and the next_24h edge case where the first start can already be in the past. These are non-obvious behaviors an agent needs to know.

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?

Purpose is front-loaded, followed by a compact, scannable list of parameter definitions. The extra details—1.5=90 min, the 15-min accuracy point, the past-start edge case—all earn their place and do not bloat the text.

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?

The description covers the core algorithm and parameter semantics, including a genuinely important edge case, and the output schema removes the need to describe return values. It is incomplete only in that the optional home_id parameter is undocumented, leaving the agent to guess its role from the schema alone.

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?

Given 0% schema coverage, the description compensates by explaining duration_hours (fractional hours, rounding up), resolution (allowed values and precision effects), window (allowed values), and contiguous (block vs individual hours). The only gap is home_id, which is neither explained in the schema nor the description.

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 first sentence names a specific operation ('Findet die günstigsten Stunden') and a concrete resource class (consumers like washer, dishwasher, EV charger), which clearly separates it from the price-data siblings. However, it never names a sibling or an explicit boundary, so it falls just short of 5.

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?

The tool context is implied through the appliance examples and parameter docs (e.g., window/contiguous), but there is no explicit statement of when to choose this over get_price_forecast or get_current_price, nor any 'do not use when' guidance. This is useful but relies on inference.

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

Deploy Server