Skip to main content
Glama

Emission Factors

by io.github.rozetyp
OverviewDiscussionsAdmin

cleanest_hours

Read-only

Find the cleanest (lowest grid carbon) contiguous window of N hours in the day to run a flexible load (batch jobs, EV charging, pumping, HVAC pre-cooling) at a US ZIP code or balancing authority. Based on the hour-of-day pattern of the last 7 days (168 hours) of EIA-930 data, in local time. Returns the cleanest and dirtiest windows, % saved vs the daily average, and all hours ranked; between limits the windows to given local hours (e.g. overnight). A scheduling guide from recent history, not a forecast.

Input Schema

NameRequiredDescriptionDefault
baNoBalancing authority code (e.g. CISO, ERCO, PJM, MISO, NYIS). Use this OR zip.
zipNo5-digit US ZIP code (or use ba)
betweenNoOptional local hours the window must fall in, start-end, wrapping past midnight: e.g. "20-06" for an EV fleet parked overnight, "9-17" for working hours.
durationNoWindow length in hours (default 4)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / between
      Added value: +{
+  "description": "Optional local hours the window must fall in, start-end, wrapping past midnight: e.g. \"20-06\" for an EV fleet parked overnight, \"9-17\" for working hours.",
+  "pattern": "^\\d{1,2}(:00)?-\\d{1,2}(:00)?$",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / zip / pattern
      Previous value: -"^\\d{5}$"New value: +"^\\d{5}(-?\\d{4})?$"
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only carry readOnlyHint, so the description does real work: it discloses the data source (last 7 days / 168 hours of EIA-930), the local-time basis, and that results are historical rather than predictive. It does not mention auth requirements, rate limits, or fallback behavior when a ZIP cannot be mapped to a BA.

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?

Purpose and scope are front-loaded in the first sentence, with data basis and return values following. The third sentence is a dense semicolon-joined run-on that packs return contents and the `between` behavior together, which is efficient but slightly harder to parse.

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 compensates by enumerating the returns (cleanest and dirtiest windows, % saved vs daily average, all hours ranked) and by stating the data vintage, timezone, and forecast caveat. The only minor gap is geo-resolution failure behavior, which is not essential to correct invocation.

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 description coverage is 100%, so all four parameters are already documented in the schema, making 3 the baseline. The description adds only a paraphrase of the `between` semantics (window limited to given local hours, e.g. overnight) and the default duration, which the schema already states; no extra syntax or interaction rules (e.g. zip vs ba precedence) are contributed.

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?

States a specific verb and resource — find the cleanest contiguous N-hour window for a flexible load — and immediately scopes it to a ZIP code or balancing authority. The parenthetical '(lowest grid carbon)' removes ambiguity about what 'cleanest' means, and the wording separates it from sibling tools like hourly_intensity or calculate_emissions.

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?

Gives concrete use cases (batch jobs, EV charging, pumping, HVAC pre-cooling) and explicitly says it is 'a scheduling guide from recent history, not a forecast,' which is the key decision boundary against forecast-style siblings. It stops short of naming an alternative tool by name and offers no explicit when-not-to-use case beyond the forecast caveat.

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

All Emission Factors toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources