Skip to main content
Glama

iaqualink_add_schedule

Adds a run program to a Jandy AquaLink RS panel schedule via iAqualink WebTouch. Set circuit, start/stop times and days, then save and confirm with a re-read.

Instructions

Add a program to a Jandy AquaLink RS panel’s own schedule (iAqua systems), through iAqualink WebTouch — the panel emulation the iAqualink web app uses. Picks the circuit by its panel label (e.g. "Filter Pump", "Pool Light", "Cleaner"), sets start and stop (24-hour HH:MM; stop may be earlier than start to run overnight) and run days, saves, and re-reads the list to confirm. The preview shows the schedule list before and after. Asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE).

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": {
      "serial": "<serial>",
      "circuit": "<circuit>",
      "start": "<start>",
      "stop": "<stop>",
      "days": "<days>"
    },
    "name": "iaqualink_add_schedule"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysYesRun days as the panel names them: All, M, Tu, W, Th, F, Sa, Su, Wkdays or Wkends
stopYesStop time, 24-hour HH:MM
startYesStart time, 24-hour HH:MM
serialYesSystem serial number, from iaqualink_list_systems
circuitYesCircuit label as the panel names it
confirmTokenNoONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true. The description adds genuinely useful behavior beyond them: a mandatory user confirmation gate, a before/after preview, and a post-write re-read to verify. It does not contradict any annotation, though it also doesn't warn about failure modes (e.g. panel rejecting a duplicate or full schedule).

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 action and target, then the mechanics, then the confirmation contract — a sensible order with no filler sentences. The parenthetical explaining WebTouch as panel emulation is slightly indulgent but does aid understanding of why the tool exists.

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?

For a mutation tool with no output schema, the description covers what an agent needs: required inputs' semantics, the confirmation protocol including the fallback token flow, and what the preview returns. The two-phase confirmation ambiguity, which would otherwise be the biggest failure risk, is fully resolved.

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 coverage is 100%, so all six parameters are already documented in the schema, including the day enum and HH:MM pattern. The description adds real meaning on top: stop-before-start means overnight operation, and circuit is a panel-native label rather than an ID. These are helpful clarifications but the schema baseline already carries most of the load.

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?

Specific verb+resource: 'Add a program to a Jandy AquaLink RS panel's own schedule' plus the transport (iAqualink WebTouch) and the fields it sets. An agent immediately knows this creates a new schedule entry. It does not explicitly state how it differs from siblings like iaqualink_edit_schedule or iaqualink_set_schedule, leaving that boundary to inference from the verb 'Add'.

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?

Clear operational context: pick the circuit by panel label, use 24-hour HH:MM, stop may precede start for overnight runs, and a user confirmation must happen before the write. The confirmation-path branching (elicitation vs. preview + confirmToken) is spelled out with explicit 'never on the first call, never invented, never reused'. What's missing is exclusionary guidance — nothing says to use edit_schedule instead when the program already exists.

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