Skip to main content
Glama

Future Micro Mold Lab

Process capability (Cp, Cpk, Pp, Ppk)

process_capability
Read-onlyIdempotent

Judge whether a running process can hold a dimension inside its tolerance. Reports Cp and Cpk from within-subgroup sigma and Pp and Ppk from overall sigma — the second pair is what a customer's SPC package computes from the same measurements — each with a 95% confidence interval, an upper bound on parts per million out of spec, and an Anderson–Darling normality check. Estimators follow Minitab's defaults. No verdict is given when the data cannot support one (no limit, zero spread, badly non-normal data). One specification limit is enough. Sample at least 25 consecutive parts without adjusting the process.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "process_capability"
  }
}

Input Schema

NameRequiredDescriptionDefault
lslNoLower specification limit
uslNoUpper specification limit
targetNoNominal from the drawing. Used only to sanity-check it against usl/lsl (a warning when it falls outside them) — not carried into the share link, since the snapshot has no field for it.
samplesNoMeasurements in production order
study_codeNoA study as the Lab card encodes it; use instead of the measurements (samples, usl, lsl, target, subgroupSize, withinMethod)
subgroupSizeNoConsecutive measurements per rational subgroup. Omit or 1 for individuals (within sigma from the moving range).
withinMethodNoWithin-sigma estimator when subgroupSize > 1: pooled standard deviation (default, as Minitab) or R-bar/d2.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only establish read-only/idempotent safety; the description adds substantial behavior beyond that — 95% confidence intervals, a PPM out-of-spec upper bound, an Anderson–Darling normality check, Minitab-default estimators, and the explicit refusal to issue a verdict on unsupportable data. These are exactly the outputs and failure modes an agent needs to interpret the result, and none of it is duplicated from the structured fields.

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?

The verdict-relevant statement comes first, followed by what is reported, then defaults, then failure conditions, then data requirements — a clean front-loaded ordering. Every sentence carries distinct information; the em-dash aside about what a customer's SPC package computes is the only elaboration, and it clarifies rather than pads.

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 seven optional parameters, no output schema and only safety annotations, the description carries the full explanatory burden and does so: it defines the returned statistics, their estimator basis, the uncertainty reporting, the normality check, and the degenerate-data cases. An agent can both call and interpret this tool without further context.

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%, so the schema already documents lsl, usl, target, samples, study_code, subgroupSize and withinMethod, and the description adds little parameter-level syntax of its own. Its genuinely additive points ('one specification limit is enough', minimum 25 consecutive parts, no adjustment during sampling) are sampling-design guidance rather than parameter semantics, so the baseline of 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?

The first sentence gives a specific verb and object — 'judge whether a running process can hold a dimension inside its tolerance' — and the second enumerates the exact statistics returned (Cp, Cpk from within-subgroup sigma; Pp, Ppk from overall sigma). The purpose is unmistakable and self-differentiating from a measurement-system study, but the description never names a sibling or states the boundary versus them.

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

Usage Guidelines4/5

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

It gives concrete preconditions: 'One specification limit is enough' and 'Sample at least 25 consecutive parts without adjusting the process', plus explicit when-not conditions ('No verdict is given when ... no limit, zero spread, badly non-normal data'). It stops short of naming an alternative tool or prerequisite workflow (e.g. running a gage study first), so there is no routing guidance to siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources