Constitutional AI kernel with 13 MCP tools, 888_JUDGE verdict pipeline, and VAULT999 ledger.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 8 tools
Each tool has a clearly distinct purpose: init starts the session, observe gathers evidence, think reasons, judge arbitrates, forge executes, memory manages recall, route dispatches, seal archives. No two tools appear to do the same thing; even memory and seal are differentiated by mutability (governed recall vs immutable sealing).
All tools follow the arif_ prefix with a verb-like token (forge, init, judge, observe, route, seal, think) except 'memory' which is a noun. This is a minor deviation from the verb pattern, but the overall convention is consistent and predictable.
With 8 tools, the set is well-scoped for a constitutional AI kernel. Each tool corresponds to a core system function (initialization, observation, reasoning, judgment, execution, memory, routing, sealing) without redundancy or bloat.
The tool surface covers the main lifecycle: init, observe, think, judge, forge (execute), memory, route, and seal. Minor gaps include no explicit session termination or reset tool, and no direct audit/reporting tool (though init mentions audit), but these are not critical dead ends for the kernel's core purpose.
KERNEL 777 · Execution gate via A-FORGE — mutates only after SEAL verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | engineer | |
| query | No | ||
| plan_id | No | ||
| actor_id | No | ||
| manifest | No | ||
| _envelope | No | ||
| session_id | No | ||
| arif_ack_id | No | ||
| artifact_id | No | ||
| session_token | No | SCT from arif_init — continuity for ChatGPT multi-call path | |
| vault_entry_id | No | ||
| seal_verdict_id | No | ||
| ack_irreversible | No | ||
| judge_state_hash | No | ||
| approved_action_hash | No | ||
| constitutional_chain_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds that mutation occurs 'only after SEAL verdict,' which provides some behavioral context beyond the annotations' destructiveHint. However, it does not elaborate on what mutation entails, what gets affected, or any side effects. Given annotations already indicate destruction, this is marginal improvement.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (single sentence), but it sacrifices clarity and completeness. While brevity is valued, essential information is missing, making it less useful than a slightly longer but more informative description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's high complexity (16 parameters, no output schema, cryptic sibling names), the description is completely inadequate. It does not explain the tool's purpose in practical terms, the meaning of modes, or how to use it effectively, leaving major gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With only 6% schema description coverage, the description fails to compensate by explaining any of the 16 parameters. Only one parameter (session_token) has a schema description. The tool description adds no parameter meaning, leaving the agent with minimal guidance for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description indicates it is an execution gate that mutates only after a SEAL verdict, but the purpose is vague and does not clearly explain what the tool does concretely. The cryptic phrasing 'KERNEL 777 · Execution gate via A-FORGE' lacks specificity, though it does mention a verb-resource relation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings (arif_init, arif_judge, etc.) or any context for appropriate invocation. There are no 'when-not-to-use' or alternative suggestions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 000 · Session ignition — binds actor, floors, and audit before any other arif_* verb.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | init | |
| nonce | No | ||
| intent | No | ||
| context | No | ||
| payload | No | ||
| tooling | No | ||
| verbose | No | ||
| actor_id | No | ||
| epoch_id | No | ||
| evidence | No | ||
| trace_id | No | ||
| _envelope | No | ||
| verbosity | No | minimal | |
| session_id | No | ||
| agent_policy | No | ||
| auth_context | No | ||
| counterparty | No | ||
| sovereign_id | No | ||
| session_token | No | ||
| actor_signature | No | ||
| caller_actor_id | No | ||
| delegation_mode | No | ||
| idempotency_key | No | ||
| ack_irreversible | No | ||
| executor_actor_id | No | ||
| declared_model_key | No | ||
| client_capabilities | No | ||
| requested_authority | No | OBSERVE_ONLY | |
| previous_session_hash | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds the ordering constraint ('before any other arif_* verb'), but otherwise relies on annotations. It does not disclose specific side effects, authentication requirements, or error behavior. Given that readOnlyHint=false and idempotentHint=false are already present, the additional behavioral context is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense sentence that is front-loaded with a title-like header. It is concise and avoids waste, but the heavy jargon makes it cryptic rather than clearly structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the high complexity (29 params, no output schema), a one-sentence metaphor is wholly inadequate. No return values, side effects, prerequisites, or error conditions are described.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 29 parameters and 0% schema description coverage, the description provides no guidance on any parameter. Terms like 'actor' and 'audit' are not mapped to schema fields, leaving agents without clues for correct usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses metaphor ('ignition', 'binds') and jargon ('actor, floors, audit') without explaining the functional purpose. It implies a session initialization step but does not clearly state what the tool does or how it differs from sibling tools like arif_think or arif_observe.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'before any other arif_* verb' explicitly indicates that this tool should be used first as an initialization step. However, it does not provide exclusions or mention alternatives, so it is clear but lacks full comparative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 666 · Constitutional verdict — binding SEAL/HOLD/SABAR/VOID arbitration.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | judge | |
| nonce | No | ||
| domain | No | ||
| key_id | No | ||
| actor_B | No | ||
| actor_id | No | ||
| evidence | No | ||
| _envelope | No | ||
| actor_Phi | No | ||
| candidate | No | ||
| claim_text | No | ||
| session_id | No | ||
| action_tier | No | standard | |
| claim_class | No | ||
| niat_params | No | ||
| action_class | No | ||
| blast_radius | No | ||
| seal_purpose | No | ||
| session_token | No | ||
| context_source | No | ||
| heart_critique | No | ||
| vault_entry_id | No | ||
| actor_signature | No | ||
| entropy_pathway | No | ||
| entropy_receipt | No | ||
| authority_effect | No | ||
| cooldown_entry_id | No | ||
| sovereign_receipt | No | ||
| reversibility_level | No | ||
| requested_capability | No | ||
| constitutional_chain_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), lowering the bar. The description adds the outcome classes SEAL/HOLD/SABAR/VOID and the 'binding' nature of the verdict, but it does not explain side effects, output shape, error behavior, or how 'binding' relates to the read-only hint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The single line is short but not usefully concise: decorative 'KERNEL 666' and undefined 'SABAR' consume space that should carry meaning. This is under-specification rather than efficient communication.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 31 parameters, no parameter descriptions, and no output schema, this description is wholly inadequate. An agent cannot determine which parameters are needed for a verdict, what the response looks like, or what the outcome classes mean.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description names none of the 31 parameters or their semantics. The outcome labels do not map to fields such as mode, claim_text, evidence, authority_effect, or reversibility_level, so the description does not compensate for the schema's silence.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The phrase 'Constitutional verdict — binding SEAL/HOLD/SABAR/VOID arbitration' indicates that the tool issues verdicts with certain outcome classes, so it is more than a tautology. However, it is cryptic and never plainly states what the tool does or how it differs from siblings like arif_route or arif_seal.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no conditions for use, no exclusions, and no alternative tools. It does not say when to call arif_judge instead of arif_route, arif_seal, or arif_think, leaving applicability entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 555 · Memory governor — L1–L6 governed semantic recall, storage, and persistence.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Operation mode: recall, inspect, attest, remember, promote, revise, forget, audit, metabolize. | recall |
| tier | No | Memory tier L1–L6. | |
| query | No | Semantic search query (recall/audit). | |
| content | No | Text body for remember mode. | |
| payload | No | Mode-specific params dict (truth_class, provenance, structured, etc.). | |
| to_tier | No | Destination tier for promote. | |
| actor_id | No | Calling actor (F11 attribution). | |
| lease_id | No | Governed lease ID. | |
| trace_id | No | Trace ID for audit. | |
| memory_id | No | Target memory UUID (inspect/promote/revise/forget). | |
| session_id | No | Governing session. | |
| new_content | No | Replacement content for revise. | |
| session_token | No | SCT from arif_init. | |
| human_approval | No | Explicit human approval for promote/forget gates. | |
| idempotency_key | No | Idempotency key for write operations. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds little behavioral context beyond the annotations. While destructiveHint=true already flags mutating behavior, the description does not disclose that modes like forget, revise, or promote are destructive, nor that human_approval may gate certain operations. The 'storage and persistence' phrasing is consistent with annotations but provides no additional operational warning or nuance.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, which is efficient, but it opens with 'KERNEL 555 ·' flavor text that does not earn its place. The phrasing 'L1–L6 governed semantic recall' is slightly cryptic, though not verbose. It is adequately concise but not exemplarily structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a complex tool with 15 parameters, 9 modes, and destructive behavior, yet the description is only one line. It does not explain what modes such as attest, metabolize, or audit mean, when human_approval is required, or how to combine parameters like memory_id and new_content for revise. The absence of an output schema further increases the burden on the description, which it does not meet.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 15 parameters individually, including the mode enum. The description does not add meaningful parameter-level semantics beyond the 'L1–L6' tier concept, so it stays at the baseline for a fully self-documenting schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies the tool as a 'Memory governor' handling 'L1–L6 governed semantic recall, storage, and persistence,' which clearly names the resource (memory) and core operations. It is distinct from the sibling tools by domain, though the verb 'govern' is abstract and doesn't explicitly differentiate it from siblings in text. Overall it provides a clear, non-tautological purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no guidance on when to use this tool versus alternatives. It does not mention any sibling tools, decision criteria, or example scenarios, leaving the agent to infer usage from the name and mode enum alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 111 · Sense reality into evidence with epistemic tags and uncertainty bounds.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| mode | No | search | |
| query | No | ||
| layers | No | ||
| actor_id | No | ||
| _envelope | No | ||
| session_id | No | ||
| result_limit | No | ||
| session_token | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, providing a safe behavioral profile. The description adds that the tool produces 'evidence with epistemic tags and uncertainty bounds,' which gives some extra context but doesn't elaborate on side effects, auth needs, or rate limits. The annotations carry most of the burden, so a 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (one sentence), which is concise, but it sacrifices substance. For a tool with 9 parameters and no output schema, the brevity leads to under-specification. It is not appropriately sized for the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (9 parameters, 0 required, no output schema), the description provides almost no complete picture. It mentions epistemic tags and uncertainty but omits what the tool returns, how modes differ, and how parameters interact. The annotations help but cannot compensate for the lack of concrete operational details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, meaning the description does not explain any of the 9 parameters. Cryptic parameters like '_envelope', 'layers', and the eight distinct modes (e.g., 'entropy_dS', 'compass') are left entirely unexplained. The agent cannot determine how to set values correctly based on the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses poetic language ('sense reality into evidence') but lacks concrete specifics about what the tool does. It hints at gathering data with epistemic tags but doesn't clarify the operation. The name 'observe' and 'KERNEL 111' suggest a sensing function, but the purpose is vague compared to sibling tools like arif_forge or arif_judge.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like arif_memory or arif_judge. There is no mention of prerequisites, exclusions, or contextual triggers, making it hard for an agent to decide when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 444 · Intent→organ router — dispatches to GEOX/WEALTH/WELL/A-FORGE.
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | Alias for intent (backward compat). | |
| organ | No | Optional explicit organ override. If provided, intent matching is skipped and this organ is used directly. | |
| intent | No | Natural-language description of what the user wants. e.g. "interpret this seismic section", "assess portfolio risk" | |
| actor_id | No | Calling actor. | |
| _envelope | No | ||
| arguments | No | Arguments to pass to organ_tool. | |
| mission_id | No | Explicit human-cockpit mission binding (investigate|interpret| decide|build|monitor|remember). When set, skips keyword classification and binds the six-mission plan. Preferred over free-text when the agent already knows the mission. | |
| organ_tool | No | The tool name on the target organ to call. If absent, returns routing decision only (no bridge call). | |
| session_id | No | Governing session. | |
| session_token | No | SCT from arif_init (ChatGPT continuity). | |
| contract_c_kwargs | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=true, idempotentHint=true) already declare the safety profile, so the description carries less burden. It adds the target organ names (GEOX/WEALTH/WELL/A-FORGE) but does not disclose whether it executes the target tool or just returns a routing decision, which is a key behavioral nuance.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, front-loaded with the core purpose ('KERNEL 444 · Intent→organ router'), and every word contributes meaning. No wasted text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is complex (11 optional parameters, no output schema), but the description does not explain return values, the optional routing decision vs. bridge call behavior, or how to use the parameters. Critical context is missing for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is high (82%), so the schema already documents most parameters. The description adds minimal extra meaning beyond identifying the routing targets, and it does not compensate for the undocumented parameters (e.g., _envelope, contract_c_kwargs).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as an 'Intent→organ router' with a specific dispatch function to GEOX/WEALTH/WELL/A-FORGE. This distinguishes it from sibling tools like arif_forge or arif_think, which have different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used for routing intents to organs, but it does not explicitly state when to use it versus alternative tools or provide any exclusion scenarios. The 'router' label gives contextual cues but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 999 · VAULT999 immutable append — irreversible civilizational memory sealing.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | seal | |
| nonce | No | ||
| payload | No | ||
| actor_id | No | ||
| _envelope | No | ||
| session_id | No | ||
| drift_events | No | ||
| seal_purpose | No | ||
| witness_type | No | ai | |
| session_token | No | ||
| constitutional | No | ||
| actor_signature | No | ||
| ack_irreversible | No | ||
| judge_state_hash | No | ||
| constitutional_chain_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true, and the description's word 'irreversible' aligns with that, so no contradiction. However, the description adds no meaningful behavioral context beyond the annotation—it doesn't disclose what data gets destroyed, what appends to the ledger, whether session tokens or actor signatures are required, or what ack_irreversible gates. For a destructive tool with no other context, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (a single sentence), which could be seen as concise. However, this is under-specification rather than efficient conciseness—there is virtually no actionable content. It front-loads branding language but provides no substantive guidance, so brevity is not earned.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 15 parameters, no output schema, no param coverage, and only two annotations, the description is profoundly inadequate. The tool appears to be a complex sealing/ledger operation with multiple modes, cryptographic fields (actor_signature, judge_state_hash, nonce), and side effects (irreversible, destructive). A single cryptic sentence cannot make such a tool safely invocable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must bear full responsibility for explaining the 15 parameters. The description mentions none of them—not mode, not payload, not seal_purpose, not ack_irreversible, not actor_signature. The mode enum offers six distinct operations with zero explanation. This is a severe gap for a tool with 15 parameters and no param documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses cryptic 'KERNEL 999 · VAULT999 immutable append — irreversible civilizational memory sealing' phrasing. It conveys that this is an append/sealing operation with irreversible memory implications, but the verb and resource are obscured behind brand-like labels. It doesn't clearly state what action the agent performs or distinguish from siblings like arif_forge or arif_judge.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The mode parameter offers distinct operations (seal, verify, ledger, audit, session_close) but the description doesn't explain when each should be selected or how this differs from sibling tools. The 'ack_irreversible' flag hints users must acknowledge irreversibility, but no guidance exists on the decision process.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KERNEL 333 · Mind — structured reasoning under F2/F7 with OBS/DER/INT/SPEC labels.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | reason | |
| query | No | ||
| plan_id | No | ||
| actor_id | No | ||
| _envelope | No | ||
| session_id | No | ||
| witness_type | No | ai | |
| session_token | No |
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.
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.
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.
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.
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.
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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
arif_judge2 fields changedInput schema / properties / claim_classAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+}Input schema / properties / claim_textAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null
+}arif_memory2 fields changedInput schema / properties / mode / descriptionPrevious value: -"Operation mode: recall, inspect, attest, remember, promote, revise, forget, audit, etc."New value: +"Operation mode: recall, inspect, attest, remember, promote, revise, forget, audit, metabolize."Input schema / properties / mode / enumPrevious value: -[
- "recall",
- "inspect",
- "attest",
- "remember",
- "promote",
- "revise",
- "forget",
- "audit"
-]New value: +[
+ "recall",
+ "inspect",
+ "attest",
+ "remember",
+ "promote",
+ "revise",
+ "forget",
+ "audit",
+ "metabolize"
+]Constitutional AI governance: 11 mega-tools, 13 floors, VAULT999 ledger. Human-in-loop by design.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Shared long-term memory vault for AI agents with 20 MCP tools.
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Add one secure layer between your agents and this server.