Skip to main content
Glama
Yacine-ai-tech

AgentKit

by Yacine-ai-tech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Forecast Metric

forecast_metric

Project future KPI values from historical monthly data, returning Monte Carlo confidence intervals and upper/lower bounds across a chosen horizon.

Instructions

Generate forward-looking time-series forecasts with Monte Carlo confidence intervals for a named KPI.

Applies trend analysis and linear projection mathematical modeling over historical monthly metric data to predict future trajectory across specified forward horizon periods, providing upper and lower bound confidence intervals.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
periodsNoNumber of monthly periods ahead to project. Defaults to 6 periods (range: 1 to 24).
metric_nameYesExact or substring name of the KPI metric to forecast (e.g. 'revenue', 'mrr', 'gross_margin', 'headcount', 'cac', 'active_users', 'churn_rate').
confidence_levelNoStatistical confidence interval band width (e.g. 0.95 for 95% confidence interval). Defaults to 0.95.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.16
    • addedInput schema / properties / confidence_level / description
      Added value: +"Statistical confidence interval band width (e.g. 0.95 for 95% confidence interval).\nDefaults to 0.95."
    • addedInput schema / properties / metric_name / description
      Added value: +"Exact or substring name of the KPI metric to forecast (e.g. 'revenue', 'mrr',\n'gross_margin', 'headcount', 'cac', 'active_users', 'churn_rate')."
    • addedInput schema / properties / periods / description
      Added value: +"Number of monthly periods ahead to project. Defaults to 6 periods (range: 1 to 24)."
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does disclose meaningful behavior: the modeling approach (trend analysis and linear projection), the probabilistic method (Monte Carlo), and the result shape (upper/lower confidence bounds). It does not state that this is a read-only computation or note any cost/rate/permission constraints, which is the remaining gap.

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 first sentence is strong and front-loaded, but the second is bloated with redundant phrasing ('forward-looking' vs 'predict future trajectory', 'trend analysis and linear projection mathematical modeling'). It could convey the same method detail in roughly half the words.

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?

An output schema exists, so return values need not be re-explained, and the description covers purpose, method, and output concept for a 3-parameter tool. What is missing is the when-to-use routing and any operational caveats, but overall it is nearly complete for 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 description coverage is 100%, so periods, confidence_level, and metric_name are already fully documented in the schema. The description merely restates horizon and confidence-interval concepts without adding format or default guidance beyond the schema; baseline 3 applies.

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 ('Generate forward-looking time-series forecasts ... for a named KPI') and names the concrete output (Monte Carlo confidence intervals). It is clearly distinguishable from siblings like query_kpis (retrieval) and detect_kpi_anomalies (anomaly detection).

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 implied by 'forward-looking' and 'predict future trajectory' versus the historical orientation of siblings, but the description never states when to choose this over query_kpis or get_executive_summary, nor any prerequisites. Implied context only, no exclusions.

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

Deploy Server

Other Tools