Skip to main content
Glama
mcp-edf

mcp-edf

by mgcrea

EDF: Electricity Consumption

edf_get_electricity_consumption
Read-only

Retrieve daily or monthly electricity consumption in kWh and euros from the Linky meter, including cost totals, standing charges, and peak/off-peak or Tempo splits.

Instructions

Electricity used per day or per month, in kWh and in euros, from the Linky meter via EDF Suivi Conso. Each row has the total cost, the daily share of the subscription (standing_charge_eur), and, on a peak/off-peak or Tempo contract, the split by tariff heading. total sums the range and gives the average price per kWh. Costs are EDF's own estimate at the contract's prices, taxes included; they track the bill closely but are not the invoice. Rows flagged nature other than REAL are estimates. Use step=month for anything over a few months: a year of days is ~25 kB.

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": {
      "from": "<from>"
    },
    "name": "edf_get_electricity_consumption"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoLast day, INCLUSIVE, as YYYY-MM-DD, e.g. 2026-10-31. Defaults to yesterday: the meters report once a day, and a day's figures usually land the next morning around 08:00.
fromYesFirst day, inclusive, as YYYY-MM-DD in Paris time, e.g. 2026-10-01.
stepNoday: one row per day (at most 400 days). month: one row per calendar month (at most ~3 years).day

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the read-only and open-world profile, and the description adds genuinely non-obvious behavior: costs are EDF's own estimate at contract prices (not the invoice), rows with `nature` other than REAL are estimates, and a full year of daily rows is ~25 kB. It does not mention any authentication prerequisite, which is the main remaining gap.

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?

Purpose is front-loaded in the first clause, followed by return shape, then cost caveats, then the one operational rule. No sentence is filler, and the density is appropriate for a data-heavy tool.

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?

With no output schema, the description does the work of explaining return fields (total, standing_charge_eur, tariff split, `total` range summary) and their caveats, which is exactly what an agent needs. Auth requirements and any rate-limit behavior are the only notable 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 coverage is 100%, so the baseline is 3, but the description adds practical meaning to `step` beyond the schema's hard limits — it recommends month granularity for ranges over a few months and quantifies the payload cost. `from`/`to` get no extra semantics beyond the schema, but nothing is misleading.

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?

The opening sentence gives a specific resource (electricity used), granularity (per day or per month), units (kWh and euros), and the data source (Linky meter via EDF Suivi Conso). That framing naturally separates it from a load curve, max-power, or gas-consumption tool without needing to name them.

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?

The only explicit guidance is parameter-level: 'Use step=month for anything over a few months,' with a concrete size rationale. There is no guidance on when to choose this tool over siblings like edf_get_usage_breakdown or edf_compare_periods, so tool selection is left to inference.

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