sima

Overview Schema Source Related Servers Discussions Admin

characterize

Transforms each raw time series individually with Box-Cox lambda, differencing, seasonality checks, and outlier scan, then records analyst overrides for subsequent modeling.

Instructions

N0c — Each raw series' transformation, with art's engine and in art's order: lambda (Box-Cox, 0 or 1), d (ADF + KPSS, art's policy: one step at a time), seasonality (HAC F-test; harmonics proposed when detected) and a preliminary outlier scan (reported, not treated). Each series keeps its OWN lambda and d — no joint consensus: forcing them alike was the old sima's first fault.

set records the analyst's changes on top of the proposal: "MINK: lam=0, d=0; MUSKRAT: d=1, harmonics=no" (keys lam, d, D, harmonics). It is the starting point of both routes (U: the univariate models first; V: the vector first).

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": {
      "name": "<name>"
    },
    "name": "characterize"
  }
}

Input Schema

Name	Required	Description	Default
`set`	No
`name`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 30, 2026

TDQS

C2.8/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose useful behavior: the transform is proposed per-series, outliers are "reported, not treated," harmonics are proposed only when detected, and analyst `set` values override proposals. It never states whether the tool writes state, whether it is idempotent, or what permissions/cost apply — gaps that matter for an un-annotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The headline sentence front-loads the substance, but the text is weighed down by opaque jargon ("art's engine," "N0c," "the old sima's first fault") and editorializing about a previous tool's mistake. The warning about not forcing lambda/d alike does earn its place as a semantic constraint, but several phrases do not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the two-parameter surface is small. Still, for a tool with zero annotation coverage and a 0%-described schema, the description should clarify the required `name` argument and whether the characterization is persisted — omissions that leave an agent guessing before 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 coverage is 0%, so the description must compensate. It does well for `set`, documenting the exact syntax, the accepted keys (lam, d, D, harmonics) and a worked example. It says nothing about `name`, the sole required parameter, leaving the agent to infer whether it is a dataset, a series group, or a model name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the concrete outputs (Box-Cox lambda, differencing order d via ADF+KPSS, seasonality via HAC F-test, preliminary outlier scan), so the operation is inferable. But it opens with the cryptic label "N0c" and never states a verb or resource plainly — the reader must reconstruct that this characterizes each raw series in a pipeline step. An agent cannot distinguish it from siblings like build_univariate or identify_matrices on the basis of the text alone.

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

Usage Guidelines2/5

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

The only usage signal is that `set` is "the starting point of both routes (U: the univariate models first; V: the vector first)," which hints at sequencing but names no sibling tool and gives no explicit when/when-not. There is no statement of prerequisites or of what to do instead if the series is already characterized.

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