netatmo energy mcp

Detect unusual heating behaviour

netatmo_detect_anomalies

Read-onlyIdempotent

Detect unusual room readings in Netatmo 30-minute data—implausible jumps, constant or missing values, rapid setpoint drops, and sustained setpoint deviations—with severity and evidence.

Instructions

Rule-based detection of unusual readings in 30-minute room data (default: last 24 h, at most 14 days): implausible values or jumps, constant readings, missing data, rapid drops at a constant setpoint, sustained deviation from the setpoint. Each finding has severity, confidence, evidence and an explanation; findings are observations, not diagnoses.

Input Schema

Name	Required	Description
`to`	No	Range end, ISO 8601. Defaults to now when "from" is given.
`from`	No	Range start, ISO 8601 (e.g. 2026-01-15 or 2026-01-15T07:30). Without an offset it is read in the home time zone.
`period`	No	Named period in the home time zone. Alternative to from/to.
`home_id`	No	Home ID from netatmo_list_homes. Optional when the account has a single home.
`room_id`	No	Room ID from netatmo_list_rooms.
`room_name`	No	Limit to one room (default: all rooms)
`max_anomalies`	No	Maximum findings returned, most severe first (default 30)

Output Schema

Name	Required	Description	Default
`home`	Yes
`notes`	Yes
`range`	Yes
`scale`	Yes
`caveats`	Yes
`requests`	Yes
`anomalies`	Yes
`truncated`	Yes
`anomaly_count`	Yes
`rooms_analysed`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.2Oct 23, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already establish that the tool is read-only, idempotent, and non-destructive, and the description adds substantial behavioral context: the detection is rule-based, operates on 30-minute readings, has a bounded default and maximum range, and returns findings with severity, confidence, evidence, and explanation. It also clarifies that findings are observations, not diagnoses.

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?

The description is compact and front-loaded: it leads with the detection method and data scope, then enumerates anomaly types, then describes findings. Every sentence contributes useful information without redundancy.

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

Completeness5/5

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

With read-only annotations, full schema coverage, and an output schema present, the description supplies everything the agent needs: the detection scope, time bounds, anomaly categories, and the structure and interpretive limits of findings. No critical behavioral or output information is missing.

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 description coverage is 100%, so the input schema fully documents the seven parameters. The description adds only indirect parameter context through the default window and maximum 14-day range, which is consistent with the baseline of 3 when the schema carries the main documentation burden.

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 operation, rule-based detection of unusual readings, and scopes it to 30-minute room data with a bounded time window. This clearly distinguishes it from sibling tools that retrieve summaries, statuses, or histories rather than detecting anomalies.

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 description gives useful context such as the default last 24 hours and maximum 14-day window, but it does not explicitly state when to choose this tool over siblings like netatmo_get_temperature_history or netatmo_get_heating_summary. Usage is implied by the anomaly-detection purpose rather than spelled out.

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

Deploy Server