aivy-mcp

Official

Overview Schema Source Related Servers Discussions Admin

set_energy_mode

Switch a solar site's energy mode to self-consumption, AI price-driven trading, or time-boxed manual charge/discharge windows, so battery power follows your chosen strategy.

Instructions

CHANGES THE SITE (control scope). Confirm with the user before calling.

mode: selfConsumption (inverter default), amber_smart (Ai+, price-driven trading) or forced (manual windows). forced is always time-boxed: duration_minutes (default 240, max 1440); afterwards the server returns the site to the mode it had before. Shorthand for forced: action=charge|discharge with power_w and target_soc (charge) or stop_soc (discharge) builds one window starting now. Or pass explicit time_slots: [{type, start 'HH:MM', end 'HH:MM', target_soc|stop_soc, power, pace}] in site local time. variant picks the Ai+ engine when mode is amber_smart. The SOC floor and export limits cannot be overridden. Takes effect on the engine's next tick (about a minute).

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": {
      "site_id": "<site_id>",
      "mode": "<mode>"
    },
    "name": "set_energy_mode"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	Yes
`action`	No
`power_w`	No
`site_id`	Yes
`variant`	No
`stop_soc`	No
`target_soc`	No
`time_slots`	No
`duration_minutes`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.9.0Nov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations supplied the description carries the full burden and does well: it discloses that forced mode is time-boxed, that duration defaults to 240 and caps at 1440, that the server reverts to the prior mode afterwards, that SOC floor and export limits cannot be overridden, and that changes land on the next engine tick (~1 minute). It doesn't mention permissions/auth or failure behavior, which keeps it off a 5.

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 scope and the confirmation requirement, then flows from simple mode choice to advanced overrides; nearly every clause carries new information. The telegraphic line breaks and all-caps phrasing make it feel denser than it is, but there is little true filler.

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 need no explanation, and for a 9-parameter mutation with zero annotation and zero schema-description support the description covers the mode semantics, time-boxing, revert behavior, and slot format needed to call it correctly. Minor gaps around 'variant' and 'pace' are the only real omissions.

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 0% across 9 parameters, so the description must compensate and largely does: mode values are enumerated, duration_minutes gets a default and max, action=charge|discharge is tied to power_w plus target_soc/stop_soc, and time_slots is spelled out with field names and 'HH:MM' local-time format. Only 'pace', valid 'type' values, and variant's accepted values remain unstated.

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?

Opens with a specific verb and resource ('CHANGES THE SITE') and scopes it as control-plane, then enumerates the three mode values so the agent knows exactly what state it is setting. It never names the read counterpart get_energy_mode, so the boundary between setting and reading must be inferred.

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?

Gives clear context for each mode (inverter default, Ai+ price-driven trading, manual windows) and states the precondition 'Confirm with the user before calling', plus offers two equivalent calling styles (shorthand vs explicit time_slots). It stops short of saying when to prefer this over siblings like update_ai_plus or plan_best_price_discharge.

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