ReliaSim

run_showcase

LIVE experiment — run a bottling-line demo against the real ReliaSim engine with parameters you choose, and get its verbatim run envelope (metadata, execution stats, metrics, details). This is the only tool that COMPUTES fresh output: dial duration_days (or buffer capacities on the bs4 demos) and see the real numbers for that exact configuration. IMPORTANT: a run_showcase result is NOT a verified reference number — it is live output for the parameters you passed. Label it as an experiment result, not a canonical figure, and don't blend it with the curated reference numbers. For the canonical, verified OEE/throughput/bottleneck values use find_bottleneck / run_gain_loss / run_buffer_tradeoff instead. Quote any figures verbatim; do not round, average, or derive.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`knobs`	No	Optional parameters as a map of name:number. All eight demos accept `duration_days` (run length, 7–90 days). The two Buffer-Options demos also accept buffer capacities: bs4-ct → `buffer_capacity_b3` / `buffer_capacity_b4` / `buffer_capacity_b5`; bs4-leds → `buffer_capacity_b2` / `buffer_capacity_b3` / `buffer_capacity_b4` (each 0–10000 units). Unknown names are rejected; out-of-range values are clamped to the allowed range by the engine.
`demo_id`	Yes	Which bottling-line demo to run live. Same eight ids as the curated tools (bs1-ct … bs4-leds).

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations provided, the description fully discloses behavioral traits: it is a live experiment, output is not a verified reference, should not be blended with curated numbers, and figures must be quoted verbatim. These details go well beyond the schema and inform the agent about the nature and limitations of the tool.

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 substantial but every sentence earns its place: it defines the tool, states its unique compute nature, delivers a critical warning about non-canonical status, and offers alternative tools. The IMPORTANT marker structures the warning clearly, with no redundant or filler content.

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?

For a tool with no output schema, the description adequately explains the return envelope categories (metadata, execution stats, metrics, details) and the experimental nature. It covers the essential use case, limitations, and alternatives. Sibling tools are clearly distinguished, making the description complete for an agent to select and invoke 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 description coverage is 100%, so the baseline is 3. The description adds context about using duration_days universally and buffer capacities on bs4 demos, but this information is already present in the knobs object's schema. No additional semantic value beyond emphasizing the live configuration.

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 states a specific verb and resource: 'run a bottling-line demo against the real ReliaSim engine' and get its 'verbatim run envelope'. It explicitly differentiates from siblings by claiming it is the only tool that COMPUTES fresh output, contrasting with curated reference tools.

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 explicit when-to-use and when-not-to-use guidance. It warns that run_showcase results are not verified reference numbers, instructs labeling as experiment results, and directs users to find_bottleneck / run_gain_loss / run_buffer_tradeoff for canonical values. Also specifies to quote figures verbatim and not to derive.

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

All ReliaSim 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

A4.5/5.0

Disambiguation5/5

Each tool targets a distinct operation: comparison, concept explanation, bottleneck analysis, facts, narrative, buffer sweep, gain/loss, and live custom runs. Even the experimental tools have clear boundaries (buffer vs interrupt vs custom parameters), so no overlapping purposes exist.

Naming Consistency5/5

All tool names follow snake_case with a verb_noun pattern (compare_chapters, explain_concept, find_bottleneck, get_chapter_facts, get_chapter_narrative, run_buffer_tradeoff, run_gain_loss, run_showcase). While verbs vary, they appropriately reflect the action, and the structure is uniform.

Tool Count5/5

8 tools is within the ideal 3-15 range for a domain-specific server. Each tool earns its place, covering explanation, analysis, comparison, and experiments without redundancy or bloat.

Completeness4/5

The tool set covers conceptual learning, chapter details, bottleneck analysis, comparison, and three types of experiments, which is comprehensive for a simulation analysis server. The only minor gap is the lack of a tool to list available chapters, which could hinder discoverability for agents unfamiliar with the dataset.

Resources

Need Help?