Skip to main content
Glama

arifOS — Constitutional AI Kernel

by io.github.ariffazil

333 Think · Mind

arif_think
Read-onlyIdempotent

KERNEL 333 · Mind — structured reasoning under F2/F7 with OBS/DER/INT/SPEC labels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoreason
queryNo
plan_idNo
actor_idNo
_envelopeNo
session_idNo
witness_typeNoai
session_tokenNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize",
-  "simulate",
-  "wonder"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate",
+  "wonder",
+  "atlas"
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize",
-  "simulate"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate",
+  "wonder"
+]
  4. Changed1 schema field changed
    • removedInput schema / properties / intent
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
  5. Changed1 schema field changed
    • addedInput schema / properties / intent
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  6. Changed1 schema field changed
    • addedInput schema / properties / session_token
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  7. Changed1 schema field changed
    • changedInput schema / properties / mode / enum
      Previous value: -[
-  "reason",
-  "reflect",
-  "verify",
-  "critique",
-  "axioms",
-  "plan",
-  "plan_review",
-  "plan_approve",
-  "refactor_plan",
-  "metabolize"
-]New value: +[
+  "reason",
+  "reflect",
+  "verify",
+  "axioms",
+  "plan",
+  "plan_review",
+  "plan_approve",
+  "refactor_plan",
+  "metabolize",
+  "simulate"
+]
  8. Changed3 schema fields changed
    • addedOutput schema / additionalProperties
      Added value: +true
    • removedOutput schema / properties
      Removed value: -{
-  "_nine_signal_compliant": {
-    "description": "Internal compliance flag",
-    "type": "boolean"
-  },
-  "_violations": {
-    "description": "Non-compliance audit trail",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "actor_id": {
-    "description": "Sovereign or agent actor ID",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "delta_S": {
-    "description": "Thermodynamic entropy change",
-    "type": "number"
-  },
-  "meta": {
-    "description": "Metadata including actor_id, mode, circuit",
-    "type": "object"
-  },
-  "nine_signal": {
-    "description": "F2 addendum nine-signal block",
-    "type": "object"
-  },
-  "output_policy": {
-    "description": "Policy constraints: DOMAIN_SEAL, DOMAIN_HOLD, DOMAIN_VOID, SIMULATION_ONLY",
-    "type": "string"
-  },
-  "reasons": {
-    "description": "Human-readable justification list",
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "result": {
-    "description": "Tool-specific payload",
-    "type": "object"
-  },
-  "session_id": {
-    "description": "Active session identifier",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "stage_progression": {
-    "description": "Next stage auto-chain hint",
-    "type": [
-      "object",
-      "null"
-    ]
-  },
-  "status": {
-    "description": "Execution status: OK, ERROR, TIMEOUT, DRY_RUN",
-    "type": "string"
-  },
-  "timestamp": {
-    "description": "ISO-8601 timestamp",
-    "type": "string"
-  },
-  "tool": {
-    "description": "Canonical tool name that produced this response",
-    "type": "string"
-  },
-  "verdict": {
-    "description": "Constitutional verdict: SEAL, HOLD, VOID, SABAR, PROVISIONAL, PARTIAL",
-    "type": "string"
-  }
-}
    • removedOutput schema / required
      Removed value: -[
-  "status",
-  "tool",
-  "verdict",
-  "result",
-  "nine_signal",
-  "reasons"
-]
  9. First observed

TDQS

D1.9/5.0
Behavior3/5

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

The annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which already cover the safety profile. The description adds 'structured reasoning' behavior but uses undecipherable labels (OBS/DER/INT/SPEC) without explaining what outputs or side effects occur. Since annotations are rich and the description doesn't contradict them, it earns a baseline 3 but adds minimal distinct behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence and highly concise. However, its brevity is under-specification rather than efficient communication; the jargon-laden content ('F2/F7', 'OBS/DER/INT/SPEC', 'KERNEL 333') fails to serve the reader. It is technically short but not well-structured for comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with 8 parameters, a 12-value enum, no output schema, and no parameter documentation. The description explains none of the mode semantics, the purpose of plan_id/actor_id/session_id/witness_type/token, or what 'structured reasoning' produces. For an agent to use this tool correctly across 12 different modes without any field or behavior documentation is effectively impossible.

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

Parameters1/5

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

The schema description coverage is 0%, and the description provides zero parameter explanations. The most important parameter is 'mode' with a 12-value enum (reason, reflect, verify, axioms, plan, plan_review, plan_approve, refactor_plan, metabolize, simulate, wonder, atlas), none of which are described. The description references 'OBS/DER/INT/SPEC' but never maps them to the mode values or query semantics. With 8 parameters and 0% coverage, the description fails entirely to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'KERNEL 333 · Mind — structured reasoning under F2/F7 with OBS/DER/INT/SPEC labels' references internal jargon ('KERNEL 333', 'F2/F7', 'OBS/DER/INT/SPEC') with no explanation. It states 'structured reasoning' but does not clearly state what the tool does, what a user achieves by calling it, or how it differs from siblings like arif_judge or arif_observe. For an agent without domain-specific context, this is nearly opaque.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The description mentions 'structured reasoning' but never states when an agent should invoke arif_think instead of arif_forge, arif_judge, or arif_route. No when-to-use, when-not-to-use, or alternative references are provided.

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

All arifOS — Constitutional AI Kernel toolsInspect
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

C2.8/5.0
Disambiguation4/5

Each tool targets a distinct kernel function: initialization, observation, reasoning, judgment, routing, execution, memory, and sealing. The abstract descriptions could cause slight confusion, but the KERNEL labels and verb-noun distinctions make roles reasonably clear.

Naming Consistency4/5

All tools share the 'arif_' prefix and are mostly single verbs (init, observe, think, judge, route, forge, seal) but 'memory' is a noun, breaking the pattern slightly. Naming is otherwise consistent and predictable.

Tool Count5/5

Eight tools provide a well-scoped surface for a constitutional AI kernel, covering initiation, perception, reasoning, arbitration, execution, memory, and immutable sealing. The count feels appropriate for the stated purpose without redundancy or bloat.

Completeness4/5

The kernel covers the core lifecycle: init, observe, think, judge, act, and store. Minor gaps exist, such as the absence of a tool for updating or amending constitutional rules, but the primary workflows are supported.

Resources