ASTRA

tcai_meta_learning

Track meta-learning convergence by computing learning velocity from reward-prediction-error variance; optionally inject an RPE sample to flag novel or confusing regimes.

Instructions

Meta-learning state (MetaLearningModule port): learning velocity from RPE-variance dynamics. velocity>0 ⇒ converging; noveltySpike ⇒ novel/confusing regime. Optionally inject an RPE sample.

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_meta_learning"
  }
}

Input Schema

Name	Required	Description	Default
`rpe`	No	Inject a reward-prediction-error sample ∈ [−1,1]

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already disclose the full profile: readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false, so the agent knows injection mutates state. The description adds interpretative semantics (velocity>0 ⇒ converging; noveltySpike ⇒ novel/confusing regime), which is real value, but it never says how injection affects subsequent reads (reset vs. accumulate) or what the returned state contains.

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?

Three compact sentences, purpose front-loaded before the interpretative gloss and the optional injection note. No filler, though the telegraphic jargon and arrow notation make it slightly harder to parse than plain prose.

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

Completeness3/5

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

With no output schema, the description must carry the return-value burden, and it only partially does: it explains how to interpret velocity and noveltySpike but not the shape of the state object or the effect of injecting rpe. For a mutable, non-idempotent, zero-required-param tool this leaves meaningful gaps.

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% and the single optional 'rpe' parameter is fully documented in the schema (type, bounds [−1,1], meaning). The description merely restates 'Optionally inject an RPE sample', adding no syntax or behavioral detail beyond the schema, so the baseline 3 applies.

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 states a specific resource (meta-learning state) and the mechanism behind it (learning velocity derived from RPE-variance dynamics), and the title clarifies the dual read/inject mode. It is distinguishable from siblings like tcai_metaconsciousness or tcai_curiosity, though the dense jargon ('RPE-variance dynamics', 'regime') assumes domain familiarity.

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: an agent can infer you call it to check convergence (velocity>0) or a novel regime (noveltySpike), and that rpe may be supplied to inject a sample. There is no explicit when-to-use versus sibling tools (e.g. tcai_convergence, tcai_metrics) and no stated prerequisites or exclusion conditions.

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

Deploy Server