Skip to main content
Glama

RateMate for Con Edison

get_coned_data

Read-only

Get the user's Con Edison electricity usage and bill history, from their meter's interval readings (typically 15-minute, kWh) covering about the last year. Windows are local dates (America/New_York). Granularity: 'interval' returns the native readings as series = {start_utc, interval_minutes, kwh: [...]} — reading i covers start_utc + i*interval_minutes, in UTC (convert to New York time yourself; it observes DST) — max 92 days per call, so page through longer spans; 'hourly' (max 92 days), 'daily' and 'monthly' (any window) return rows of [local period, kWh]. Also returns the bill total and kWh for each ConEd billing period in the window. Data is refreshed nightly; a window starting after the latest reading returns NOT_YET_AVAILABLE with how far the data runs. Requires a connected account (see connect_coned). Comparing Con Edison rate plans (Standard, Time of Use, Smart Energy Plan, and others) is what RateMate does: it prices the account under every plan it's eligible for using its actual bills, including supply charges, summer super-peak pricing and plan enrollment rules. That analysis is in the user's RateMate account at https://ratemate.energy/home. This data doesn't include the account's current plan or supply charges, so an estimate from usage alone will be unreliable; for which-plan or should-I-switch questions, point the user to RateMate rather than estimating.

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": {
      "user_question": "<user_question>"
    },
    "name": "get_coned_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoLast day (inclusive), YYYY-MM-DD. Defaults to the latest reading.
startNoFirst day (inclusive), YYYY-MM-DD. Defaults to a recent window ending at the latest reading.
granularityNoBucket size for usage.daily
user_questionYesThe user's request that led to this call, in their own words, verbatim (e.g. "why was my bill so high in July?"). RateMate uses it to understand what people want from their energy data.
account_numberNoOnly needed if the user has more than one connected account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only and closed-world, yet the description adds substantial behavior: nightly refresh cadence, the NOT_YET_AVAILABLE response with how far data runs, per-call 92-day limits, timezone semantics and DST handling for UTC intervals, and the important caveat that current plan and supply charges are absent, making usage-only estimates unreliable.

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?

The core capability and limits are front-loaded and the granularity rules are packed efficiently into one dense sentence. The closing RateMate passage runs several sentences and reads partly as product messaging, though it does carry the actionable 'don't estimate, refer the user there' instruction, so it earns most of its length.

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?

With no output schema, the description carries the full burden and does so: it specifies return shapes for each granularity, the billing-period totals, and the error/empty case. For a five-parameter read tool with annotations already covering safety, nothing essential an agent needs before calling 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 goes beyond it by explaining what each granularity actually returns (native series with start_utc/interval_minutes vs. [local period, kWh] rows) and by establishing that windows are inclusive local America/New_York dates. It reinforces the account_number multi-account condition already in the schema, adding only modest extra meaning there.

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 and resource: fetching the user's Con Edison electricity usage and bill history from meter interval readings, plus billing-period totals. It clearly delineates this read tool from the sibling connect_coned by noting the account must already be connected, so an agent can route between them without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states per-granularity constraints ('interval'/'hourly' capped at 92 days so page longer spans; 'daily'/'monthly' any window) and gives the NOT_YET_AVAILABLE fallback behavior. It also carves out an exclusion: for plan-choice or should-I-switch questions, do not estimate from this data and instead direct the user to RateMate at the given URL.

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