Skip to main content
Glama

Battery Payback

Home battery payback estimate

calculate_payback
Read-only

Yearly saving and simple payback time of a home battery in the UK, from the user's own figures. Same model as the calculator on batterypayback.co.uk. Rates in pence per kWh.

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": {
      "annual_use_kwh": "<annual_use_kwh>",
      "battery_usable_kwh": "<battery_usable_kwh>",
      "battery_price_gbp": "<battery_price_gbp>",
      "peak_rate_p": "<peak_rate_p>"
    },
    "name": "calculate_payback"
  }
}

Input Schema

NameRequiredDescriptionDefault
loan_rateNoOptional yearly loan interest rate, 0-0.5 (charged monthly).
loan_yearsNoOptional loan term in years (with loan_rate).
peak_rate_pYesNormal or peak unit rate, p/kWh.
cheap_rate_pNoCheap-hours rate, p/kWh. Omit for a single-rate tariff.
daytime_shareNoShare of use between 8am and 4pm, 0-1. Default: the measured London profile (about 0.34, Low Carbon London smart meters).
export_rate_pNoExport (SEG) rate, p/kWh. Default 0.
annual_use_kwhYes
charge_power_kwNoOptional battery charging power, kW. With cheap_window_hours it caps grid charging at power x hours a night.
charge_from_gridNoFill the battery at the cheap rate. Default true.
battery_price_gbpYesInstalled price.
cheap_hours_shareNoShare of use already in cheap-rate hours, 0-1. Default 0.
battery_usable_kwhYes
cheap_window_hoursNoOptional length of the cheap-rate window, hours.
solar_kwh_per_yearNoYearly solar generation. 0 = no panels.
round_trip_efficiencyNo0-1, from the datasheet. Default 0.9 (assumption).
yearly_saving_declineNoOptional yearly reduction of the saving, 0-0.2.
shiftable_evening_shareNoOptional share (0-1) of evening use the household moves to cheap hours itself, without a battery. The saving is then only what the battery adds on top.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a pure offline calculation. It adds real context beyond that: the results are an estimate from a named model, and rates are in pence per kWh. It also names the two return values (yearly saving and payback time), which matters since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with what is computed, then provenance, then units. Nothing is redundant and no sentence restates the tool title alone.

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?

For a 17-parameter model with no output schema, the description covers the outputs, provenance, and unit convention, while the schema covers the rest at high density. It could go further on default assumptions and the limits of the estimate, but it is complete enough to call the tool correctly.

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 coverage is 88%, so the baseline is 3, but the sentence 'Rates in pence per kWh' genuinely disambiguates the many *_rate_p parameters (pence, not pounds or percent) that the schema descriptions state only per-parameter. That is a meaningful cross-parameter clarification, though other nuances such as how optional tariff parameters interact are left to the schema.

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?

States a specific computation (yearly saving and simple payback time) for a specific resource (home battery, UK) from user-supplied figures. The read-only calculation nature clearly separates it from the sibling get_*/list_* lookup tools, though no sibling is named explicitly.

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?

'from the user's own figures' implies the tool needs full user inputs rather than fetching data, and 'Same model as the calculator on batterypayback.co.uk' anchors the expected semantics. It gives no explicit when-to-use/when-not guidance and does not route the agent to get_battery or get_methodology for supporting facts.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources