Skip to main content
Glama
ryanpag3

coolercontrol-mcp

by ryanpag3

Create custom_sensor

create_custom_sensor

Creates custom sensors by combining temperature or metric sources with mix functions or time-based averaging, so CoolerControl can monitor calculated values and use them in fan control.

Instructions

Create a custom sensor. Required: id (unique; becomes the sensor's name) and cs_type. cs_type Mix: mix_function (Min | Max | Delta | Avg | WeightedAvg | Sum) and sources: [{temp_source: {device_uid, temp_name}, weight}]. File: file_path. Offset: offset, optional scale, one source. TimeAverage / ExponentialMovingAvg: time_window_seconds (1-300), one source. Optional metric (Temp default; Duty | Load | RPM | Freq use channel_source instead of temp_source in sources).

Input Schema

NameRequiredDescriptionDefault
fieldsYesFields using the daemon's names, as returned by the list tool

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the description does not need to establish the basic safety profile. It adds useful behavior such as id being unique and becoming the sensor name, but omits duplicate-id handling, error behavior, permissions, and what creation returns.

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 description is front-loaded with the action and then moves into required fields and variant rules. It is dense and telegraphic, but every clause carries construction information and there is no filler.

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?

For a complex nested create operation, the description covers most of the domain-specific field construction needed to call the tool. However, it does not explain the relationship to the fields wrapper, duplicate-id behavior, or return value, which matters more because no output schema exists.

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?

The schema is only a generic fields object, so the description adds substantial meaning by documenting required id and cs_type and by defining the mix, file, offset, time-average, and exponential-moving-average variants. It stops short of explicitly tying these fields to the fields wrapper and does not cover every possible field.

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 clearly states the specific verb and resource: create a custom sensor. It is distinct from update_custom_sensor and delete_custom_sensor by name, though it does not explicitly call out sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives required fields and variant-specific construction rules, but does not explain when to use this tool versus update_custom_sensor, list_custom_sensors, or other alternatives. There is no explicit prerequisite or exclusion guidance.

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