DiscreteRate

run_showcase

Read-only

LIVE EXPERIMENT — run a DRS demo against the real 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: pick a demo_id and dial its knobs (e.g. stop_time run length, or the MTBF/MTTR/goal knobs on the plant demos) to see the real numbers for that exact configuration. IMPORTANT: a run_showcase result is NOT a verified reference number — unlike the run_* tools (run_fast_slow_drain / run_hamburger_duo / run_valdez_tanker / run_vegetable_plant / run_chocolate_processing), which return curated, canonical reference values. Present run_showcase output as a live experiment result for the parameters passed; don't blend it with the curated reference numbers. 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. fast_slow_drain / hamburger_duo accept `stop_time` (run length in minutes, 1–100000). valdez_tanker accepts `duration_days` (run length in days, 1–365; it drives the circulating-ship items loop). vegetable_full accepts `making_goal` (units, 0–100000), `making_mtbf` / `making_mttr` / `packing_mtbf` / `packing_mttr` (hours, 0–1000). chocolate_processing accepts `bp_goal` (units, 0–100000), `breaker_mtbf` / `breaker_mttr` (hours, 0–1000), `changeover_delay` (hours, 0–48). Unknown names are rejected; out-of-range values are clamped by the engine.
`demo_id`	Yes	Which DRS demo to run live against the real engine.

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=true, which the description complements by emphasizing that output is a live experiment, not a verified reference, and by instructing users to quote figures verbatim. This adds important context about the output's nature and variability beyond the annotations, though it does not contradict them.

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?

The description is a dense but well-structured paragraph that front-loads the key message ('LIVE EXPERIMENT') and uses clear formatting (caps, bold) to highlight critical warnings. Every sentence adds value, though it is somewhat longer than strictly necessary; the structure makes it scannable.

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?

Given the absence of an output schema, the description adequately explains what the tool returns (run envelope with metadata, execution stats, metrics, details) and how to interpret it. It also covers the essential distinction from reference tools and provides presentation guidance, making it sufficiently complete for the tool's complexity.

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?

The input schema covers both parameters thoroughly (100% coverage), including per-demo knob ranges and validation behavior. The description adds examples ('stop_time', MTBF/MTTR knobs) but these are already present in the schema's knob description, so the description provides little additional semantic value beyond emphasizing the 'live' aspect.

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 clearly identifies the tool as a live experiment runner for DRS demos, explicitly stating it returns a 'verbatim run envelope' and is 'the only tool that COMPUTES fresh output.' It distinguishes itself from sibling run_* tools that return curated reference values, making the purpose unambiguous.

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?

The description provides explicit when-to-use guidance: use when you want live, parameterized results from the real engine, not verified reference numbers. It names the alternative run_* tools that return curated canonical values and warns strongly not to blend outputs, making the usage context clear.

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

All DiscreteRate 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

A4.4/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose: the explain_* tools each target a different DRS concept, list_drs_demos and describe_demo handle discovery/context, and each run_* tool executes a specific demo. run_showcase is explicitly differentiated as a live experiment generator, so there is no ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with lowercase and underscores (explain_*, run_*, list_, describe_). This makes the API predictable and easy to navigate.

Tool Count5/5

With 14 tools, the server sits comfortably in the ideal 3-15 range. The count is well-scoped for its purpose: a mix of educational explainers, demo discovery, and demo execution tools, each earning its place.

Completeness5/5

The tool surface is comprehensive for the DRS demo domain: users can discover demos (list_drs_demos), get detailed context (describe_demo), learn core concepts (explain_*), run fixed reference demos (run_*), and perform custom experiments (run_showcase). No significant gaps hinder the intended workflows.

Resources

Need Help?