Systems Intelligence Performative Commercial Benchmarking

create_pilot_configuration

Read-only

Generate a validated pilot configuration JSON with cohort size, duration, and metrics for AI operator benchmarking. Then run pre-deployment checks via validate_pilot_configuration.

Instructions

Generate a saveable pilot configuration JSON from parameters. Returns a validated configuration object with cohort size, duration, selected metrics, eval families, and benchmark classes. Use list_pilot_options first to see available options. The returned configuration can be passed to validate_pilot_configuration for pre-deployment checks. Configuration includes governance metadata (DEVELOPMENTAL label, no punitive use, association-not-causation evidence standard).

Input Schema

TableJSON Schema

Name	Required	Description
`metrics`	No	Array of metric IDs to include (e.g., ['leverage', 'yield', 'token_snr', 'construction']). See list_pilot_options for the full catalog.
`cohort_size`	No	Number of operators in the pilot cohort (e.g., 25, 50, 100). Determines statistical power and minimum detectable effect size.
`duration_days`	No	Pilot duration in days (e.g., 30, 60, 90). Longer windows improve intervention re-evaluation stability.

Output Schema

TableJSON Schema

Name	Required	Description
`valid`	Yes	Whether the configuration passed validation
`warnings`	No	Non-blocking validation warnings
`synthetic`	Yes	Whether data is synthetic
`configuration`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.4.3Aug 28, 2026

changedInput schema / properties / cohort_size / description

Previous value: -"Number of operators in the pilot cohort (e.g., 25, 50, 100)"New value: +"Number of operators in the pilot cohort (e.g., 25, 50, 100). Determines statistical power and minimum detectable effect size."

changedInput schema / properties / duration_days / description

Previous value: -"Pilot duration in days (e.g., 30, 60, 90)"New value: +"Pilot duration in days (e.g., 30, 60, 90). Longer windows improve intervention re-evaluation stability."

changedInput schema / properties / metrics / description

Previous value: -"Array of metric IDs to include (e.g., ['leverage', 'yield', 'token_snr', 'construction'])"New value: +"Array of metric IDs to include (e.g., ['leverage', 'yield', 'token_snr', 'construction']). See list_pilot_options for the full catalog."

addedOutput schema / properties / configuration / properties / benchmark_classes

Added value: +{
+  "description": "Selected benchmark class IDs",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / configuration / properties / cohort_size / description
```
Added value: +"Number of operators in the cohort"
```
addedOutput schema / properties / configuration / properties / duration_days / description
```
Added value: +"Pilot duration in days"
```

addedOutput schema / properties / configuration / properties / eval_families

Added value: +{
+  "description": "Selected evaluation family IDs",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / configuration / properties / governance

Added value: +{
+  "description": "Governance metadata including evidence labels and usage constraints",
+  "type": "object"
+}

addedOutput schema / properties / configuration / properties / metrics / description
```
Added value: +"Selected metric IDs"
```
addedOutput schema / properties / synthetic / description
```
Added value: +"Whether data is synthetic"
```

addedOutput schema / properties / valid / description

Added value: +"Whether the configuration passed validation"

addedOutput schema / properties / warnings

Added value: +{
+  "description": "Non-blocking validation warnings",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

First observedv0.4.0Aug 27, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotation only declares readOnlyHint=true; the description adds that the result is a 'validated configuration object,' that it is 'saveable' rather than persisted, and that governance metadata is embedded (DEVELOPMENTAL label, no punitive use, association-not-causation). These are behavioral details beyond what annotations already provide.

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?

Four sentences with the main action front-loaded, followed by workflow and governance context. There is no filler, though the governance metadata sentence is nonessential for invocation and makes it slightly longer than the leanest possible definition.

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 generation tool with complete schema documentation, an output schema, and read-only annotations, the description is self-sufficient: it covers prerequisites, downstream validation, return contents, and governance metadata. Nothing essential for selecting and calling the tool is missing.

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 schema already documents all three parameters with examples, giving 100% coverage, so the baseline is 3. The description merely restates 'cohort size, duration, selected metrics' at a high level and adds no parameter-specific semantics beyond the schema.

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 and resource: 'Generate a saveable pilot configuration JSON from parameters.' It lists the returned object's components (cohort size, duration, selected metrics, eval families, benchmark classes) and distinguishes the tool from siblings by naming list_pilot_options and validate_pilot_configuration as adjacent workflow steps.

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 explicit workflow context: 'Use list_pilot_options first to see available options' and 'can be passed to validate_pilot_configuration for pre-deployment checks.' It does not explicitly state when not to use this tool or name alternative tools for different scenarios, so it falls just short of full exclusion guidance.

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