ReliaStats

describe_bottling_line

Read-onlyIdempotent

Return the full worked-example doc for the bottling-line paired model — topology (5 machines: Filler/Capper/Labeler/Case Packer/Palletizer, 100 bottles/min, Weibull(30,1) TTF + Weibull(5,1) downtime at the Constraint-Level rollup), the two tracks (CT rollup vs LEDS-Level drill-down to 36 named failure modes), the 4 build sequences (BS1 → BS4), the file-shape mapping between ReliaSim outputs and ReliaStats modes, and a worked cross-MCP tool chain. Optional 'section' parameter narrows to one H2 section. ANTI-FABRICATION: content is sourced from docs/paired-model-bottling-line.md; every claim references the .aidos files or ChapterRegistry.fs in reliasim-site.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`section`	No	Optional H2 section name from docs/paired-model-bottling-line.md to narrow the response. Examples: 'Topology — the line itself', 'The two tracks — Constraint-Level vs LEDS-Level', 'The four build sequences (BS1 → BS4)', 'File-shape mapping — which ReliaStats mode consumes what', 'The cross-MCP workflow — worked example'. Omit to return the full doc.

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so no contradiction. The description adds valuable sourcing transparency with the ANTI-FABRICATION clause, explicitly tying content to docs/paired-model-bottling-line.md and files on reliasim-site. It also describes the optional narrowing behavior, but doesn't discuss output size or edge cases, which is acceptable given the good annotation coverage.

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 description is front-loaded with the core action and uses a structured dash list to enumerate content. The ANTI-FABRICATION sentence adds trust, and the section mention is practical. Every clause earns its place with zero fluff.

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?

For a read-only documentation tool with one optional param and no output schema, the description covers return scope, section names, and data provenance. It doesn't specify the return formatting/encoding, but that is a minor gap given annotations and the straightforward nature of the tool. Sibling context suggests the tool's niche is clear.

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% – the 'section' parameter is fully documented with examples and default behavior. The tool description merely reiterates that the parameter narrows to one H2 section but adds no new semantic information beyond the schema, so baseline 3 is appropriate.

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?

The description opens with a specific verb ('Return') and clearly scopes the resource: the full worked-example doc for the bottling-line paired model. It enumerates the exact content (topology with 5 machines, two tracks, 4 build sequences, file-shape mapping, cross-MCP tool chain), which distinguishes it from generic reliability tools like list_paired_models or explain_weibull_shape.

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?

The description implies usage context (any request needing the bottling-line paired model worked example) and even narrows scope via the optional 'section' parameter. However, it does not explicitly contrast with sibling tools or state when not to use it, so it stops short of full guidance.

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

All ReliaStats tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation3/5

Several tools overlap in purpose, particularly the explain_* family: explain_distributions_for_reliability and recommend_distribution both address distribution selection, and explain_distributions also covers Weibull β interpretation, overlapping with interpret_weibull_shape. However, descriptions are detailed enough that careful reading usually disambiguates, so the confusion is moderate rather than severe.

Naming Consistency4/5

Most tools follow a clear verb_noun pattern (compute_, describe_, explain_, interpret_, list_, recommend_), making the naming predictable. Two exceptions, 'system_reliability' and 'weibull_summary', are noun phrases without a verb, which is a minor deviation from the pattern but not disruptive.

Tool Count5/5

With 11 tools, the server is well within the ideal 3–15 range and each tool serves a distinct purpose, from educational explainers to closed-form calculation utilities. The count feels well-scoped for a reliability statistics knowledge and reference server.

Completeness4/5

The tool surface covers fundamentals, distribution guidance, Weibull calculations, availability, system reliability, and paired-model documentation, giving broad coverage of the domain. It intentionally defers fitting to an external sandbox, so the main minor gap is the lack of direct data-fitting or confidence-interval computation tools, but these can be worked around.

Resources

Need Help?