Skip to main content
Glama
aivy-mcp

aivy-mcp

Official
by IVYEnergy

create_alert

Set up threshold alerts for solar or battery metrics such as SOC, import/export price, and temperature, using above/below rules and inbox or email notifications to monitor system conditions.

Instructions

Set up a threshold alert: metric soc | import_price | export_price | temperature, operator above | below. Every firing goes to the app inbox (and the phone when the app is installed); email=True also mails the account's verified address (whoami.email_alerts says whether that works). Quiet for cooldown_minutes after each firing (min 15). An alert only tells the person something; it never changes what the battery does. Confirm the rule with the user before creating it.

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>",
      "name": "<name>",
      "metric": "<metric>",
      "operator": "<operator>",
      "threshold": "<threshold>"
    },
    "name": "create_alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
emailNo
localeNoen
metricYes
messageNo
site_idYes
operatorYes
thresholdYes
active_endNo00:00
active_startNo00:00
cooldown_minutesNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the whole burden and does well: it names the delivery channels (inbox, phone if installed, email if requested), discloses the cooldown suppression window and its 15-minute floor, and states the key non-effect ("never changes what the battery does"). Gaps remain around the active_start/active_end window and duplicate-handling, but the mutation's side effects are well communicated.

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?

Dense and front-loaded: the valid metric/operator vocabulary comes first, followed by delivery behavior, cooldown, and the safety caveat. Every sentence adds information, though the phrasing is compressed to the point of being slightly telegraphic.

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?

The output schema means return values need not be described, and the notification/cooldown/non-destructive story is complete. However, for an 11-parameter creation tool with zero schema descriptions, the silence on the active window and on how name/message/threshold are interpreted is a meaningful hole.

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 0% across 11 parameters, so the description must compensate. It defines metric, operator, email, and cooldown_minutes (including the minimum), but leaves name, site_id, threshold, message, locale, active_start, and active_end entirely undocumented — the active window in particular defaults to 00:00/00:00 with no explanation of whether that means always-on.

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?

Opens with a specific verb+resource ("Set up a threshold alert") and immediately enumerates the accepted metric values (soc | import_price | export_price | temperature) and operators (above | below). This is exactly the information the schema lacks (0% coverage, no enums), and it clearly separates the tool from siblings like list_alerts, get_alert_events, and delete_alert.

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?

Explicitly instructs the agent to confirm the rule with the user before creating it, and gives a conditional pointer (email=True requires a verified address, checkable via whoami.email_alerts). It does not name when to prefer send_test_alert_email or when creating an alert is inappropriate, but the context is otherwise unambiguous.

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