RPCS-1 Agent Tuner & Translation Bridge

Recommend AI agent configuration

recommend_agent_configuration

Read-onlyIdempotent

Diagnose why a deployed AI agent may fail. Takes environmental entropy, predictability, stakes, context horizon, and commitment style, then returns receiver profile values (TI, SG, FT, UE, AR), platform parameters (temperature, top_p, strategy), regime prediction, reasoning, and warnings. Optionally pass target_model (the actual model id) to attach MEASURED per-model receiver posture (E-LIT table): evidence-graded literalness, truth-override boundary, and translation directives. Deterministic, stateless, read-only — does not store past recommendations.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`task`	No
`environment`	No
`target_model`	No	Optional: the actual model id this agent will run on (e.g. "claude-sonnet-4-6", "deepseek-v4-pro"). When it matches a measured per-model receiver entry (E-LIT table), measured translation directives and evidence-graded posture data are attached to platform_parameters. Unknown models fall back to platform-level behavior unchanged.
`target_platform`	No	The platform whose runtime parameters should be recommended.	anthropic

Output Schema

TableJSON Schema

Name	Required	Description	Default
`warnings`	Yes
`reasoning`	Yes
`confidence`	Yes
`predicted_regime`	Yes
`receiver_profile`	Yes
`platform_parameters`	Yes
`imm_principles_applied`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 26, 2026

addedOutput schema / properties / platform_parameters / properties / receiver_evidence / properties / cb

Added value: +{
+  "description": "E-LIT-3 care boundary (1-4): highest emotional-intensity rung at which fenced answers stay bare.",
+  "type": "number"
+}

addedOutput schema / properties / platform_parameters / properties / receiver_evidence / properties / sb

Added value: +{
+  "description": "E-LIT-3 stakes boundary (1-5): highest stakes rung at which format fences still hold. Separate instrument; never pooled with li2/ob.",
+  "type": "number"
+}

Changed3 schema fields changedJul 26, 2026

addedInput schema / properties / target_model

Added value: +{
+  "description": "Optional: the actual model id this agent will run on (e.g. \"claude-sonnet-4-6\", \"deepseek-v4-pro\"). When it matches a measured per-model receiver entry (E-LIT table), measured translation directives and evidence-graded posture data are attached to platform_parameters. Unknown models fall back to platform-level behavior unchanged.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / platform_parameters / properties / receiver_evidence

Added value: +{
+  "additionalProperties": false,
+  "description": "Present only when target_model has a measured per-model receiver entry.",
+  "properties": {
+    "display_name": {
+      "type": "string"
+    },
+    "fringe": {
+      "description": "Rungs with modal comply-then-correct.",
+      "items": {
+        "type": "number"
+      },
+      "type": "array"
+    },
+    "grade": {
+      "description": "Evidence grade of the measurement — travels with the data.",
+      "enum": [
+        "confirmatory",
+        "corroboration",
+        "self_measurement"
+      ],
+      "type": "string"
+    },
+    "li2": {
+      "description": "Fenced literalness, [-1, +1].",
+      "type": "number"
+    },
+    "measured_on": {
+      "type": "string"
+    },
+    "model_key": {
+      "type": "string"
+    },
+    "ob": {
+      "description": "Truth-override boundary rung (0-5).",
+      "type": "number"
+    },
+    "scope": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "model_key",
+    "display_name",
+    "grade",
+    "li2",
+    "ob",
+    "fringe",
+    "measured_on",
+    "scope"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / platform_parameters / properties / receiver_traits

Added value: +{
+  "description": "Reliability warnings and named traits for the measured receiver.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed2 schema fields changedJun 26, 2026

addedOutput schema / properties / platform_parameters / properties / translation_notes
```
Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
```

addedOutput schema / properties / platform_parameters / properties / translation_posture

Added value: +{
+  "enum": [
+    "direct",
+    "bridging",
+    "face_preserving",
+    "minimal_clarifying"
+  ],
+  "type": "string"
+}

Changed3 schema fields changedJun 23, 2026

addedInput schema / properties / environment / default

Added value: +{
+  "commitment_style": "cautious",
+  "context_relevance": "medium",
+  "entropy": "dynamic",
+  "predictability": "somewhat_predictable",
+  "stakes": "high"
+}

addedInput schema / properties / task / default

Added value: +{
+  "domain": "customer_support",
+  "expected_duration_per_call": "medium",
+  "task_summary": "Customer support agent handling refunds, billing disputes, and policy exceptions"
+}

removedInput schema / required

Removed value: -[
-  "task",
-  "environment"
-]

Changed12 schema fields changedJun 23, 2026
- addedInput schema / properties / environment / properties / commitment_style / default
```
Added value: +"cautious"
```
- addedInput schema / properties / environment / properties / context_relevance / default
```
Added value: +"medium"
```
- addedInput schema / properties / environment / properties / entropy / default
```
Added value: +"dynamic"
```
- addedInput schema / properties / environment / properties / predictability / default
```
Added value: +"somewhat_predictable"
```
- addedInput schema / properties / environment / properties / stakes / default
```
Added value: +"high"
```
- removedInput schema / properties / environment / required
```
Removed value: -[
-  "entropy",
-  "predictability",
-  "stakes",
-  "context_relevance",
-  "commitment_style"
-]
```
- addedInput schema / properties / target_platform / default
```
Added value: +"anthropic"
```
- addedInput schema / properties / task / properties / domain / default
```
Added value: +"customer_support"
```
- addedInput schema / properties / task / properties / expected_duration_per_call / default
```
Added value: +"medium"
```
- addedInput schema / properties / task / properties / task_summary / default
```
Added value: +"Customer support agent handling refunds, billing disputes, and policy exceptions"
```
- removedInput schema / properties / task / required
```
Removed value: -[
-  "task_summary"
-]
```
- changedInput schema / required
```
Previous value: -[
-  "task",
-  "environment",
-  "target_platform"
-]New value: +[
+  "task",
+  "environment"
+]
```
First observedJun 9, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already state readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: 'Deterministic, stateless, read-only — does not store past recommendations' and explains fallback behavior for unknown models. This goes beyond the annotations, providing a clear behavioral profile.

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 composed of four sentences, each adding distinct value: purpose, input/output summary, optional parameter behavior, and determinism/statelessness. The information is front-loaded with the main purpose in the first sentence, and every sentence earns its place without redundancy.

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 tool's complexity, the description covers the environment inputs, target_model behavior, and output summary, while the output schema handles return value details. However, it never explicitly mentions the 'task' parameter, relying on schema defaults and property descriptions to fill that gap. This is adequate but not fully complete for a tool with multiple nested objects.

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 description coverage is 50% (target_model and target_platform have descriptions, while task and environment lack top-level descriptions). The description partially compensates by naming the environment factors (entropy, predictability, stakes, context horizon, commitment style) and explaining target_model's E-LIT table behavior, but it omits any explanation of the 'task' parameter and target_platform, leaving a significant gap.

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 clear verb+resource ('Diagnose why a deployed AI agent may fail') and then enumerates specific inputs and outputs, including receiver profile values, platform parameters, and regime prediction. This clearly distinguishes the tool from siblings like calibrate_profile or interpret, which focus on other aspects of agent behavior.

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 gives a clear context for use: diagnosing why a deployed AI agent may fail. It also provides optional usage guidance with target_model. However, it does not explicitly compare with sibling tools such as calibrate_profile or prepare_prompt, nor does it state when not to use this tool, so it lacks exclusionary guidance.

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

All RPCS-1 Agent Tuner & Translation Bridge tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.