Skip to main content
Glama
@three-ws/ibm-x402-mcp

@three-ws/ibm-x402-mcp

by nirholas

IBM Granite Forecast ($0.05)

ibm_granite_forecast
Read-only

Forecast numeric time series zero-shot from timestamped values and a cadence to return future horizon predictions without training.

Instructions

Zero-shot time-series forecasting via IBM Granite TTM (Tiny Time Mixer). Provide a numeric series with ISO-8601 timestamps and a cadence, receive the forecast horizon. No training required. Suitable for revenue, traffic, sensor, energy, and financial series. Use this to project a numeric series of at least 64 timestamped points forward; it returns numbers only, so pass the result to ibm_granite_analyze if you need commentary. No IBM Cloud account required — pay $0.05 USDC per call via x402.

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": {
      "timestamps": "<timestamps>",
      "values": "<values>",
      "freq": "<freq>"
    },
    "name": "ibm_granite_forecast"
  }
}

Input Schema

NameRequiredDescriptionDefault
freqYesCadence of the series as a pandas-style frequency string. Examples: 1min, 5min, 15min, 30min, 1h, 2h, 4h, 12h, 1D, 1W, 1ME.
labelNoHuman label for the series (e.g. "daily_revenue_usd"). Returned in output for traceability.
valuesYesNumeric series aligned to timestamps, oldest to newest. Must be the same length as timestamps.
timestampsYesISO-8601 timestamps at a uniform cadence, oldest to newest (e.g. ["2025-01-01T00:00:00Z", ...]).
prediction_lengthNoNumber of steps to forecast ahead. Defaults to the model horizon (typically 96 for 1h data).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.4
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv1.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing cost and payment mechanics ($0.05 USDC per call via x402, no IBM Cloud account required), that no training is needed, and that the output is numbers only. The readOnlyHint=true and idempotentHint=false annotations are consistent with a paid, read-only inference call that may not be deterministic.

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?

Front-loaded with the mechanism and the input/output contract, then constraints, then the handoff to ibm_granite_analyze, then pricing. The "Suitable for revenue, traffic, sensor, energy, and financial series" sentence is mild filler, though it does aid domain matching.

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 still conveys that the result is a bare numeric forecast and should be routed elsewhere for interpretation, and it surfaces the payment requirement. It does not describe the exact return shape (e.g. list length matching prediction_length), which is the one remaining gap for a forecasting tool.

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 the schema already documents freq, label, values, timestamps, and prediction_length with examples and bounds. The description only restates the core contract (numeric series, timestamps, cadence, horizon). The 64-point minimum is echoed but comes straight from minItems.

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 ("Zero-shot time-series forecasting via IBM Granite TTM") plus the concrete input/output contract: numeric series with ISO-8601 timestamps and a cadence in, forecast horizon out. It also differentiates itself from the sibling ibm_granite_analyze by naming that tool as the commentary layer, so an agent can pick between them without opening schemas.

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 an explicit use condition ("project a numeric series of at least 64 timestamped points forward") and an explicit alternative for the adjacent need ("pass the result to ibm_granite_analyze if you need commentary"). It stops short of stating when NOT to use it, e.g. short series, non-numeric data, or classification-style problems, so not quite a 5.

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