Skip to main content
Glama

tcai_convergence

DestructiveIdempotent

Inspect or set the recursive halting thresholds that stop a simulation only when variational free energy settles, task quality stays high, and epistemic value stays low for several cycles.

Instructions

Inspect or configure the recursive double-loop halting criterion (v2.9). With no arguments, returns the current satisfaction state and active thresholds. With arguments, updates them. The loop halts only when variational free energy has settled (|ΔF| ≤ epsFreeEnergy) AND realized task quality is high (≥ minTaskQuality) AND epistemic value is low, sustained over patience cycles — stationarity alone is insufficient (Legros 2026 §2.2/§4.3).

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": "tcai_convergence"
  }
}

Input Schema

NameRequiredDescriptionDefault
patienceNoConsecutive satisfied cycles required to halt (default 3)
maxEpistemicNoHalt threshold: expected info gain ≤ (default 0.1)
epsFreeEnergyNoHalt threshold: absolute |ΔF| ≤ (nats, default 0.02)
relFreeEnergyNoHalt threshold: |ΔF| ≤ rel·F, scale-free (default 0.03)
minTaskQualityNoHalt threshold: realized task quality ≥ (default 0.6)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the safety profile is covered structurally. The description adds genuine behavioral context: the multi-condition AND gate (|ΔF| ≤ epsFreeEnergy and task quality ≥ minTaskQuality and low epistemic value, sustained over patience), plus the caveat that stationarity alone 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.

Conciseness4/5

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

Front-loaded with the inspect/configure split before the halting mechanics, and each sentence carries substantive content. The Legros citation is a minor flourish but supports the claim rather than padding.

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?

For a 5-param, all-optional tool with no output schema, the description explains both modes and the halting semantics thoroughly. It omits what the returned satisfaction state looks like and any permission/prerequisite context, but no output schema means return-value detail is not required.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds value by naming epsFreeEnergy, minTaskQuality, and patience inside the halt logic and showing how they combine as conjunctive conditions. It does not spell out relFreeEnergy's interaction, leaving one param to the schema alone.

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?

States a specific verb+resource: 'Inspect or configure the recursive double-loop halting criterion (v2.9)', covering both read and write modes. It is clear what the tool governs, but it never distinguishes itself from nearby siblings like tcai_second_order, tcai_cycle, or orch_criterion, so an agent must infer the niche.

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?

Explicitly gives the branching rule: no arguments returns current state/thresholds, arguments update them. It also explains the halting condition, which tells the agent when the criterion is meaningful. It stops short of naming alternatives or when-not-to-use guidance.

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