Skip to main content
Glama
Sign In

Burs-IA Utils

by io.github.soyeladice-svg
OverviewDiscussionsAdmin

Percentiles y cuantiles

stats-percentile
Read-onlyIdempotent

Calcula percentiles (0-100) con método seleccionable (lineal, exclusivo, rango más cercano). Cuándo: un resultado numérico tiene que ser exacto o reproducible y no estimado. No para: calcular la estadística descriptiva de una lista de números (stats-describe). 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: Computes one or more percentiles (0-100) of a list of numbers with a selectable method (linear = Excel PERCENTILE.INC / numpy default, exclusive, nearest_rank). When: a numeric result has to be exact or reproducible instead of estimated. Not for: computing descriptive statistics of a list of numbers (stats-describe). 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.

Input Schema

NameRequiredDescriptionDefault
methodNoPercentile method: linear (Excel PERCENTILE.INC, numpy default), exclusive (PERCENTILE.EXC), nearest_rank (optional; one of: linear, exclusive, nearest_rank; default "linear").linear
valuesYesNumbers (array of number; required; at least 1 items).
percentilesNoPercentiles 0-100 (array of number; optional; default [25,50,75,90,95,99]; at least 1 items; up to 100 items).

Output Schema

NameRequiredDescriptionDefault
resultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / values / examples
      Added value: +[
+  [
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10
+  ]
+]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the 'no side effects / read-only / no network / no stored state / deterministic' sentences largely restate structured data. What genuinely adds value is the operational envelope: 64 KB JSON input, 1 s per call, 1 MB result cap — hard limits the annotations cannot express. It stops short of describing error behavior when limits are exceeded.

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?

Labeled, front-loaded sections (Cuándo / No para / Efectos / Determinista / Límites) make it skimmable, and every clause is a discrete fact. The cost is full Spanish/English duplication, which roughly doubles token length for the same information — wasteful but not disorganized.

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?

An output schema exists, so return values need not be explained, and the description still supplies the resource limits, determinism guarantee, and the sibling boundary. For a 3-parameter, single-purpose statistics tool this covers everything an agent needs to call it correctly.

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 schema already documents the method enum with its Excel/numpy equivalences, the 0-100 percentile bounds, and the default set. The description repeats the method names and percentile range but adds no syntax, ordering, or edge-case guidance (e.g. behavior when percentiles are non-integers or values are unsorted). Baseline 3 is appropriate when the schema carries the semantics.

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 (computes percentiles 0-100 of a list of numbers) plus the method selection, and explicitly contrasts with the sibling stats-describe. An agent can distinguish it from stats-describe, stats-means, or stats-histogram without opening any 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?

Uses explicit 'When:' (a numeric result must be exact or reproducible, not estimated) and 'Not for:' (descriptive statistics of a list → stats-describe) routing. The alternative sibling is named with the condition that selects it, leaving nothing to inference.

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 toolsInspect
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