Burs-IA Utils

Pronóstico por suavizado exponencial

stats-forecast

Read-onlyIdempotent

Pronostica una serie numérica con suavizado exponencial simple, Holt (tendencia) o Holt-Winters aditivo (tendencia + estacionalidad). Los parámetros se dan o se eligen con una búsqueda en rejilla determinista que minimiza el SSE. Devuelve pronóstico, ajuste y MAE/RMSE/MAPE. Cuándo: un resultado numérico tiene que ser exacto o reproducible y no estimado. No para: calcular la media móvil simple (stats-moving-average). Efectos secundarios: ninguno (solo lectura, sin red, sin estado guardado). Determinista: la misma entrada da la misma salida. Límites: entrada JSON de hasta 64 KB, 1 s por llamada, resultado de hasta 1 MB.

EN: Forecasts a numeric series with simple exponential smoothing, Holt (trend) or additive Holt-Winters (trend + season). Smoothing parameters are given or chosen by a deterministic grid search minimizing SSE. Returns forecasts, fitted values and MAE/RMSE/MAPE. When: a numeric result has to be exact or reproducible instead of estimated. [EN completo / full EN: inputSchema.description]

Input Schema

Name	Required	Description	Default
`beta`	No	Trend smoothing 0-1 (number; optional; min 0; max 1).
`alpha`	No	Level smoothing 0-1 (number; optional; min 0; max 1).
`gamma`	No	Season smoothing 0-1 (number; optional; min 0; max 1).
`method`	No	Method (optional; one of: ses, holt, holt_winters; default "holt").	holt
`series`	Yes	Observations in time order (array of number; required; at least 3 items).
`horizon`	No	Periods to forecast (integer; optional; default 3; min 1; max 1000).
`season_length`	No	Season length (holt_winters) (integer; optional; min 2; max 366).

Output Schema

Name	Required	Description	Default
`fitted`	No
`method`	No
`metrics`	No
`forecast`	No
`parameters`	No
`parameters_chosen_by`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026
- addedInput schema / properties / series / examples
```
Added value: +[
+  [
+    10,
+    12,
+    14,
+    16,
+    18
+  ]
+]
```

Changed1 schema field changedNov 1, 2026

addedInput schema / description

Added value: +"EN: Forecasts a numeric series with simple exponential smoothing, Holt (trend) or additive Holt-Winters (trend + season). Smoothing parameters are given or chosen by a deterministic grid search minimizing SSE. Returns forecasts, fitted values and MAE/RMSE/MAPE. When: a numeric result has to be exact or reproducible instead of estimated. Not for: computing the simple (stats-moving-average). Side effects: none (read-only, no network access, no stored state). Deterministic: the same input gives the same output. Limits: JSON input up to 64 KB, 1 s per call, result up to 1 MB."

First observedNov 1, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing that parameters are fitted via deterministic grid search minimizing SSE, that output is fully reproducible, and by giving hard limits (64 KB input, 1 s per call, 1 MB result) which appear nowhere in the structured fields. Minor gap: it does not say what happens on invalid input (e.g. holt_winters without a sufficient season_length) since no error behavior is described.

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 method, then the fitting behavior, then when/when-not, then effects and limits — a clean, dense single block with no filler sentences. Slight deduction for the redundant bilingual pointer to inputSchema.description, which repeats the same text the agent already has.

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, return values need not be spelled out, yet the description still names them (forecast, fitted values, MAE/RMSE/MAPE). Combined with method variants, fitting strategy, determinism and resource limits, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic value: alpha/beta/gamma are not just 'optional 0-1' — if omitted they are chosen by the SSE-minimizing grid search, which tells the agent it can leave them out. It also flags season_length as holt_winters-specific. It stops short of explaining how season_length interacts with series length.

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 (forecast) plus the exact resource (numeric series) and enumerates the three concrete model variants (ses, holt, holt_winters) with what each captures. Explicitly names the sibling it is not (stats-moving-average), so an agent can pick it out of the large stats-* family without inspecting the schema.

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

Usage Guidelines5/5

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

Provides an explicit 'Cuándo' condition (a numeric result must be exact/reproducible rather than estimated) and an explicit 'No para' exclusion pointing to the alternative stats-moving-average. That is the when / when-not / alternative triad in full.

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

All Burs-IA Utils tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?