skforecast-ai

Official

Overview Schema Source Related Servers Discussions Admin

profile

Analyze a CSV time series file to detect frequency, series and exogenous columns, and get a recommended forecaster and estimator. Returns an identifier.

Instructions

Profile a CSV file: frequency, series, exogenous columns and the recommended forecaster and estimator. Returns a profile id.

Input Schema

TableJSON Schema

Name	Required	Description
`sep`	No	Separator of the fields of the file: ',', ';' or a tabulator. When null, it is detected from the file; pass it only when an error says it cannot be told.
`target`	No	Column to forecast, or a list of columns (one series each) for wide multi-series data. Null when it is not known: the error lists the columns of the file.
`decimal`	No	Decimal mark of the file: '.' or ',' (only when the separator is not ','). When null, it is detected from the file.
`data_path`	Yes	Absolute path of a CSV file ('.csv', '.tsv', '.csv.gz' or '.tsv.gz') inside the directory the server may read. URLs are not accepted.
`date_column`	No	Column with the dates. When null, the first column holding dates is used.
`exog_columns`	No	Columns to use as exogenous variables, an empty list for none. When null, every column that is not the target, the date or the series ids. The other columns are not used.
`series_id_column`	No	Column with the series ids of long multi-series data.

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

Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is already covered. The description adds that a profile id is produced (a persistent artifact to reuse later), which is useful, but says nothing about side effects, re-profiling the same file, or whether the id is required by siblings.

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?

Two short sentences, zero filler, with the action and the output front-loaded. Nothing is repeated from the schema or annotations.

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 an output schema present and full parameter coverage, the description only needs to say what the tool is and what it returns; it does both. The one gap, chaining guidance toward plan/forecast, is minor for a profiling entry point.

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 seven parameters are already documented in detail (separator detection, target semantics, exog defaults, date/series-id columns). The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

States a concrete verb+resource ('Profile a CSV file') and enumerates what profiling yields: frequency, series, exogenous columns, and a recommended forecaster and estimator. That distinguishes it from the downstream siblings (plan, forecast, backtest), though it never names them explicitly.

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?

Usage is only implied: the mention of a 'recommended forecaster and estimator' and the returned profile id suggest this is a precursor step before plan/forecast, but the description never says when to call this versus plan or forecast, nor any prerequisites or exclusions.

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

Deploy Server