heatpump-mcp

heatpump_set_request

Propose one heat pump change (power, mode, temperature, or fan) and get a confirmation question with token—or a refusal—to read aloud before applying it.

Instructions

Ask before one change. Ask to change one setting: power (on, off), mode (heat, cool, dry, fan, auto), temperature (16 to 28 degrees) or fan (quiet, low, medium, high, auto). Changes nothing. Returns a question ('say') to read to the owner, with a token, or a refusal ('say') to read aloud.

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": {
      "setting": "<setting>",
      "value": "<value>"
    },
    "name": "heatpump_set_request"
  }
}

Input Schema

Name	Required	Description	Default
`value`	Yes
`setting`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Strong disclosure beyond the annotations: it states no state is changed, that the result is speakable text ('say') plus a token, and that a refusal can be returned. The tension with readOnlyHint=false is worth noting but is not a contradiction, since the tool writes nothing and only stages a request. Missing are token lifetime/expiry and what a refusal implies for retry.

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?

Front-loaded with the intent and the vocabulary list, no wasted preamble. The closing sentence is clumsily built ('Returns a question (\'say\') ... or a refusal (\'say\') ...'), repeating the 'say' gloss instead of stating it once.

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?

An output schema exists, so return values are largely covered, and the description still explains the say/token/refusal shape. For a staged two-phase write the one real gap is that the token's purpose and the confirming step are left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema labels both parameters with zero coverage, yet the description fully compensates by pairing each setting (power, mode, temperature, fan) with its legal values, including the 16-28 degree range. An agent can construct a valid call from the prose alone without reading the enum.

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 uses a specific verb ("Ask to change") and enumerates the exact resource surface: power, mode, temperature, fan with their permitted values. It is clearly distinguishable from a status tool and from a commit step, though it never names the sibling confirm tool, so the routing is implied rather than stated.

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 establishes the when: single-setting, ask-before-acting changes, and states that nothing is applied. What it omits is the required follow-up path: the token returned is never tied to heatpump_set_confirm, so an agent must infer from sibling names that a second call commits the change.

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

Deploy Server