Skip to main content
Glama

Calera Infinite Context (ICX) — Persistent Memory & Associative Recall

ICX Autopilot Turn (Pre-Flight & Post-Flight)

icx_autopilot_turn

Unified ICX Autopilot Pre-Flight & Post-Flight engine. Call before answering to receive a <300-token Epistemic Decision Card (containing locked rules, prior user corrections, and grounded facts), and pass learn_correction whenever the user corrects a mistake so the rule is permanently crystallized into Volumetric Memory (StoreOnceAssociation + StoreSentencePathway). Also verifies draft_claim against the ∂²=0 boundary firewall.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "icx_autopilot_turn"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoCurrent task or question to recall grounded facts and locked rules for.
space_idNoOptional memory space partition (default: 'default').
draft_claimNoOptional draft statement or conclusion to verify against the ∂²=0 boundary contradiction firewall before responding.
learn_correctionNoOptional user correction, project rule, or architectural constraint to permanently crystallize into Volumetric Memory so the agent never repeats a mistake.

Output Schema

NameRequiredDescriptionDefault
statusYes
space_idYes
tenant_idYes
latency_msYes
locked_rulesNo
grounded_factsNo
facts_retrievedYes
autopilot_shieldYes
guardrail_reasonNo
decision_card_tokensYes
contradiction_blockedYes
new_facts_crystallizedYes
epistemic_decision_cardYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations only supply readOnlyHint=false, so the description usefully adds that learn_correction 'permanently crystallizes' a rule into memory - a durable, effectively non-reversible side effect worth flagging. It also gives a size budget (<300 tokens) for the pre-flight card. However, it says nothing about latency, whether the three modes can be combined in one call, or how the modes interact, so the disclosure is incomplete for a mutating hybrid tool.

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?

Two dense sentences, front-loaded with the tool's identity and the primary call timing, with no filler. The jargon ('∂²=0 boundary firewall', 'Volumetric Memory', internal primitive names) adds noise without adding agent-usable meaning, which keeps it below a 5.

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?

An output schema exists, so return-shape explanation is not required, and the description covers both retrieval and write paths plus claim verification. The main gap is mode interaction - whether passing query, draft_claim and learn_correction together triggers all three behaviors in one call is left ambiguous.

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?

Schema description coverage is 100%, so the schema already explains query, space_id, draft_claim and learn_correction. The description reinforces the role of learn_correction and draft_claim (the ∂²=0 contradiction firewall) but adds no format, size, or interaction detail beyond the structured fields, and never mentions space_id.

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

Purpose4/5

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

The description names a specific dual role - pre-flight retrieval of an Epistemic Decision Card (locked rules, prior corrections, grounded facts) and post-flight crystallization of corrections - plus a claim-verification mode. That is concrete and distinguishable in behavior from generic siblings like icx_recall_scoped, though it never explicitly contrasts itself with recall_epistemic_context, which sounds closely related.

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?

Timing guidance is explicit and actionable: 'Call before answering' and 'pass learn_correction whenever the user corrects a mistake'. That covers the two main invocation conditions well. It stops short of naming alternatives or stating when NOT to call it (e.g. versus recall_epistemic_context), so it does not reach the top band.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.