skforecast-ai

Official

Overview Schema Source Related Servers Discussions Admin

forecast

Run a saved plan to predict future time series or evaluate on a test set, exporting predictions and metrics to CSV and returning a run ID.

Instructions

Run a plan: forecast the future, or evaluate on a test set with test_size. Predictions and metrics go to CSV files. Returns a forecast id.

Input Schema

TableJSON Schema

Name	Required	Description
`plan_id`	Yes	Id of the plan to run (from `plan`, `refine_plan` or `links.best_plan_id` of `compare`).
`exog_path`	No	Absolute path of a CSV file with the future values of the exogenous variables, one row per date (and series) of the horizon. Required to forecast the future when the plan uses exogenous variables. The script of `get_code` reads them from 'exog_future.csv' in its working directory.
`test_size`	No	Null to forecast the future. To evaluate instead, the test set: the last n observations (an integer, which must equal `steps`) or the ISO 8601 date it starts at. A fraction in (0, 1) only works when it gives exactly `steps` observations.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes
`cost`	No
`kind`	Yes
`files`	No
`links`	No
`notices`	No
`summary`	Yes
`changeable`	No
`notices_omitted`	No
`values_included`	No
`summary_truncated`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 15, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already establish it is a non-read-only, non-destructive, closed-world operation. The description adds real behavioral context beyond that: predictions and metrics are written to CSV files (a side effect) and a forecast id is returned for chaining, which the annotations do not convey.

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?

Three tight sentences, front-loaded with the action and the two modes, then the side effects and return value. No filler, though the second clause is slightly compressed.

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 annotations covering safety and an output schema covering return values, the description only needs to frame the modes and side effects, which it does. Nothing critical is missing, though the relationship to sibling tools remains unaddressed.

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 coverage is 100% and the parameter descriptions are highly detailed (exog_path semantics, test_size null vs integer vs fraction). The description adds little beyond the schema, only naming `test_size` as the evaluation switch, so the baseline 3 is appropriate.

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 gives a specific verb+resource ('Run a plan') and clearly splits into two operating modes: forecast the future, or evaluate on a test set. It is distinguishable from generic siblings, though it never contrasts itself with the adjacent `backtest`/`compare` tools.

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?

It explains when each internal mode applies (default/null `test_size` to forecast, a value to evaluate), which is genuine conditional guidance. However, it never addresses when to reach for this tool versus siblings like `backtest` or `compare`, leaving the selection implicit.

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

Deploy Server