QA Orchestrator

Overview Schema Source Related Servers Discussions Admin

Inspect server model settings

get_qa_orchestration_model_policy

Read-onlyIdempotent

Read the server-wide model policy applied to new QA orchestration sessions, showing whether host defaults or configured per-stage provider, model, and reasoning settings are used.

Instructions

Read the server-wide model policy used to create new sessions.

The mode is either host_default (use the host's configured model and reasoning) or configured (use the returned per-stage provider, model IDs, and reasoning).

Use to inspect the policy loaded for new sessions; takes no arguments.

Existing session state and current-stage policy: get_qa_orchestration(run_id).
Create a session with these settings: start_qa_orchestration.

Reads the loaded in-memory snapshot, not the current policy file; restart the server connection after file changes. No session is created and no provider is contacted; the result does not verify which model the host executed.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`mode`	Yes
`provider`	No
`deep_model`	No
`triage_model`	No
`primary_model`	No
`deep_reasoning`	No
`synthesis_model`	No
`triage_reasoning`	No
`primary_reasoning`	No
`synthesis_reasoning`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.2.18Oct 26, 2026

changedOutput schema / properties / deep_reasoning / anyOf

Previous value: -[
-  {
-    "enum": [
-      "none",
-      "minimal",
-      "low",
-      "medium",
-      "high",
-      "xhigh",
-      "max"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "none",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max",
+      "ultra"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / primary_reasoning / anyOf

Previous value: -[
-  {
-    "enum": [
-      "none",
-      "minimal",
-      "low",
-      "medium",
-      "high",
-      "xhigh",
-      "max"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "none",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max",
+      "ultra"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / synthesis_reasoning / anyOf

Previous value: -[
-  {
-    "enum": [
-      "none",
-      "minimal",
-      "low",
-      "medium",
-      "high",
-      "xhigh",
-      "max"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "none",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max",
+      "ultra"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / triage_reasoning / anyOf

Previous value: -[
-  {
-    "enum": [
-      "none",
-      "minimal",
-      "low",
-      "medium",
-      "high",
-      "xhigh",
-      "max"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "none",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max",
+      "ultra"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

Changed56 schema fields changedv0.2.5Oct 12, 2026

changedOutput schema / description

Previous value: -"The model IDs the host agent should use for each orchestration role."New value: +"Flat MCP response shape for configured and host-default model policies."

addedOutput schema / properties / deep_model / anyOf

Added value: +[
+  {
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / deep_model / default
```
Added value: +null
```
removedOutput schema / properties / deep_model / maxLength
```
Removed value: -128
```
removedOutput schema / properties / deep_model / minLength
```
Removed value: -1
```
removedOutput schema / properties / deep_model / pattern
```
Removed value: -"^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$"
```
addedOutput schema / properties / deep_model / title
```
Added value: +"Deep Model"
```
removedOutput schema / properties / deep_model / type
```
Removed value: -"string"
```

addedOutput schema / properties / deep_reasoning / anyOf

Added value: +[
+  {
+    "enum": [
+      "none",
+      "minimal",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / deep_reasoning / default
```
Previous value: -"high"New value: +null
```

removedOutput schema / properties / deep_reasoning / enum

Removed value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]

addedOutput schema / properties / deep_reasoning / title
```
Added value: +"Deep Reasoning"
```
removedOutput schema / properties / deep_reasoning / type
```
Removed value: -"string"
```

addedOutput schema / properties / mode

Added value: +{
+  "enum": [
+    "configured",
+    "host_default"
+  ],
+  "title": "Mode",
+  "type": "string"
+}

addedOutput schema / properties / primary_model / anyOf

Added value: +[
+  {
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / primary_model / default
```
Added value: +null
```
removedOutput schema / properties / primary_model / maxLength
```
Removed value: -128
```
removedOutput schema / properties / primary_model / minLength
```
Removed value: -1
```
removedOutput schema / properties / primary_model / pattern
```
Removed value: -"^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$"
```
addedOutput schema / properties / primary_model / title
```
Added value: +"Primary Model"
```
removedOutput schema / properties / primary_model / type
```
Removed value: -"string"
```

addedOutput schema / properties / primary_reasoning / anyOf

Added value: +[
+  {
+    "enum": [
+      "none",
+      "minimal",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / primary_reasoning / default
```
Previous value: -"medium"New value: +null
```

removedOutput schema / properties / primary_reasoning / enum

Removed value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]

addedOutput schema / properties / primary_reasoning / title
```
Added value: +"Primary Reasoning"
```
removedOutput schema / properties / primary_reasoning / type
```
Removed value: -"string"
```

addedOutput schema / properties / provider / anyOf

Added value: +[
+  {
+    "enum": [
+      "openai",
+      "anthropic"
+    ],
+    "title": "ModelProvider",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / provider / default
```
Added value: +null
```

removedOutput schema / properties / provider / enum

Removed value: -[
-  "openai",
-  "anthropic"
-]

removedOutput schema / properties / provider / type
```
Removed value: -"string"
```

addedOutput schema / properties / synthesis_model / anyOf

Added value: +[
+  {
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / synthesis_model / default
```
Added value: +null
```
removedOutput schema / properties / synthesis_model / maxLength
```
Removed value: -128
```
removedOutput schema / properties / synthesis_model / minLength
```
Removed value: -1
```
removedOutput schema / properties / synthesis_model / pattern
```
Removed value: -"^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$"
```
addedOutput schema / properties / synthesis_model / title
```
Added value: +"Synthesis Model"
```
removedOutput schema / properties / synthesis_model / type
```
Removed value: -"string"
```

addedOutput schema / properties / synthesis_reasoning / anyOf

Added value: +[
+  {
+    "enum": [
+      "none",
+      "minimal",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / synthesis_reasoning / default
```
Previous value: -"medium"New value: +null
```

removedOutput schema / properties / synthesis_reasoning / enum

Removed value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]

addedOutput schema / properties / synthesis_reasoning / title
```
Added value: +"Synthesis Reasoning"
```
removedOutput schema / properties / synthesis_reasoning / type
```
Removed value: -"string"
```

addedOutput schema / properties / triage_model / anyOf

Added value: +[
+  {
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedOutput schema / properties / triage_model / default
```
Added value: +null
```
removedOutput schema / properties / triage_model / maxLength
```
Removed value: -128
```
removedOutput schema / properties / triage_model / minLength
```
Removed value: -1
```
removedOutput schema / properties / triage_model / pattern
```
Removed value: -"^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$"
```
addedOutput schema / properties / triage_model / title
```
Added value: +"Triage Model"
```
removedOutput schema / properties / triage_model / type
```
Removed value: -"string"
```

addedOutput schema / properties / triage_reasoning / anyOf

Added value: +[
+  {
+    "enum": [
+      "none",
+      "minimal",
+      "low",
+      "medium",
+      "high",
+      "xhigh",
+      "max"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedOutput schema / properties / triage_reasoning / default
```
Previous value: -"max"New value: +null
```

removedOutput schema / properties / triage_reasoning / enum

Removed value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]

addedOutput schema / properties / triage_reasoning / title
```
Added value: +"Triage Reasoning"
```
removedOutput schema / properties / triage_reasoning / type
```
Removed value: -"string"
```

changedOutput schema / required

Previous value: -[
-  "provider",
-  "triage_model",
-  "primary_model",
-  "deep_model",
-  "synthesis_model"
-]New value: +[
+  "mode"
+]

addedOutput schema / title
```
Added value: +"ModelPolicyResponse"
```

Addedv0.1.16Sep 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/closed-world, yet the description adds genuinely non-obvious behavior: it reads a loaded in-memory snapshot rather than the policy file, requires a server reconnect after file edits, creates no session, contacts no provider, and does not verify what the host actually executed. These are exactly the caveats that would otherwise cause an agent to misinterpret stale results.

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?

Front-loaded with the core purpose, then a compact mode definition, then a scannable bullet list of routing alternatives and caveats. Slightly longer than strictly necessary – the mode explanation is helpful but dense – though every sentence carries information an agent needs.

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?

With an output schema present, the return shape needn't be described, and the description instead covers the interpretive semantics an agent needs (host_default vs configured modes, snapshot staleness, non-verification). Nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the baseline is 4; the description correctly confirms 'takes no arguments', which matches the empty schema. No further parameter detail is possible or needed.

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?

States a specific verb and resource ('Read the server-wide model policy used to create new sessions') and immediately scopes it to new-session policy, which separates it from get_qa_orchestration (existing session state) and start_qa_orchestration (session creation). An agent can pick it apart from the ten siblings without opening a schema.

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?

Explicitly says when to use it ('Use to inspect the policy loaded for new sessions; takes no arguments') and gives two named alternatives with the conditions that select them, covering both the read-sibling and the create-sibling. This is the when/when-not/alternatives pattern scored at the top of the range.

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

Deploy Server