Skip to main content
Glama

Solar and export summary

octopus_get_solar_summary
Read-only

Summarize solar import and export costs and earnings from Octopus smart meters over a period, including half-hourly rates and net cost; add inverter generation to calculate self-consumption.

Instructions

Combine a home's electricity import and export smart meters (for solar panels or a battery) over a period: kWh imported and exported, what the imports cost and the exports earned at the actual rate for every half-hour (so Agile Outgoing and other time-of-use export tariffs are priced correctly), standing charges and the net cost, by day, week or month. Octopus has no generation data, so to get self-consumption (generation minus export) and self-sufficiency, pass generated_kwh from your inverter app. Readings are usually a day behind. Estimates exclude discounts and credits; your bill is the source of truth.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "octopus_get_solar_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoEnd: a date (inclusive, the whole day) or date and time (default the end of yesterday)
fromNoStart: a date (YYYY-MM-DD, UK time) or date and time (default 30 days ago)
limitNoReturn at most this many rows, the most recent (default 100)
group_byNoHow to total the half-hours: day (default), week (Monday to Sunday), month or total
generated_kwhNoWhat the panels generated in the whole period, in kWh, from your inverter or generation meter. Octopus doesn't have this, so self-consumption is only worked out when you give it
account_numberNoAccount number like A-1234ABCD (default OCTOPUS_ACCOUNT, or the only account the API key can see)
export_meter_pointNoThe export MPAN, when the account has several (see octopus_get_account)
import_meter_pointNoThe import MPAN, when the account has several (see octopus_get_account)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Return at most this many rows, the most recent (default 100)",
      +  "type": "integer"
      +}
    • removedInput schema / properties / max_rows
      Removed value: -{
      -  "description": "Return at most this many rows, the most recent (default 100)",
      -  "type": "integer"
      -}
  2. First observedv0.4.1

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnly, not open-world, not idempotent), the description adds substantive behavior: readings lag about a day, half-hourly pricing to handle Agile Outgoing and time-of-use export tariffs, and estimates excluding discounts and credits. That is exactly the kind of context annotations cannot carry.

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?

The description front-loads the core output first, then the generated_kwh caveat, then the reliability caveat. It is dense but tight, with no sentence that does not add information.

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 an eight-parameter read-only aggregator with no output schema, the description says what is returned (kWh imported and exported, cost and earnings, standing charges, net cost by day, week or month) and covers freshness and estimate caveats. Nothing needed for correct invocation is missing.

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 100%, so the baseline is 3. The description adds genuine meaning beyond the schema, though: it explains why generated_kwh (whole-period generation, not per half-hour) is needed and how it drives the self-consumption and self-sufficiency fields.

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 states a specific verb and scope: combining import and export meters over a period to give kWh, cost, standing charges and net cost. This makes the summary and solar-plus-export purpose clear. It stops short of explicitly distinguishing itself from sibling octopus_get_consumption, so an agent must infer the boundary.

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?

The description gives clear usage guidance: pass generated_kwh from an inverter to get self-consumption, because Octopus has no generation data, and treat the bill as the source of truth. It does not name an alternative tool for bills or consumption, so there is no explicit when-not guidance.

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