ASTRA

tcai_active_inference

Read-onlyIdempotent

Monitor active-inference telemetry—variational free energy, expected free energy, task quality, entropy, and learned action—to inform principled halting decisions.

Instructions

Active-inference core telemetry (v2.9): the REAL variational free energy F (surprise), expected free energy G(π) decomposed into pragmatic + epistemic value, the realized task quality, the model entropy, and the Dirichlet-learned action. This is the principled quantity the halting criterion thresholds on — not a heuristic correlate (Da Costa et al. 2020; Legros 2026 §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_active_inference"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the returned values are the 'REAL' principled quantities rather than heuristic proxies, which is useful trust context, but it discloses no rate limits, auth needs, or return-shape behavior.

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 sentences, front-loaded with the tool identity and the list of returned quantities. The second sentence leans on citation scaffolding ('Da Costa et al. 2020; Legros 2026 §4.3') that does little operational work for an agent, but the text is not bloated.

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?

With no input parameters and no output schema, the description's enumeration of returned quantities (F, G(p), task quality, entropy, Dirichlet action) effectively stands in for a return-value contract. It lacks any statement of response format or structure, but for a zero-argument read it is largely sufficient.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. No meaning is lost by omission here.

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 resource — active-inference core telemetry — and enumerates exactly the quantities it surfaces (F, G(p) with pragmatic/epistemic decomposition, task quality, model entropy, Dirichlet-learned action). It distinguishes itself from the broader tcai_metrics sibling by being the active-inference-specific read, though it never states a clean verb and reads more like an abstract than a tool description.

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

Usage Guidelines3/5

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

Usage is only implied: the note that this is 'the principled quantity the halting criterion thresholds on' suggests it is relevant when inspecting why the halting criterion fires, and 'not a heuristic correlate' gestures at heuristic alternatives. There is no explicit when-to-use, when-not-to-use, or named alternative such as tcai_metrics.

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

Deploy Server