ASTRA

wm_train_step

Apply a training step to an online world model by injecting strengths into target neurons, advancing the simulation by timesteps for SNN LIF+STDP learning.

Instructions

Online World Model Training Step

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "wm_train_step"
  }
}

Input Schema

Name	Required	Description	Default
`action`	Yes	Action applied between observations

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

C2/5.0

Behavior2/5

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

Annotations disclose readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the mutation/non-idempotent profile is partially covered structurally. However, the description adds nothing: it never states that model weights are updated, whether the update persists, what 'online' implies, or what the action is applied between. For a state-mutating training tool this is a substantial gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

It is a single four-word phrase with no wasted words, but this is under-specification rather than conciseness. There is no front-loaded statement of purpose, effect, or constraints to anchor the agent.

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

Completeness2/5

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

The tool takes a nested action object (with duration/strengths/targetNeurons), has no output schema, and is a non-idempotent mutation — the description should at minimum explain the effect on the world model and any return or side effects. None of that is present, leaving the agent without a basis for correct invocation.

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%: duration, strengths [mV], and targetNeurons are documented in the schema, and 'action' itself is described as 'Action applied between observations'. The description adds no syntax or semantic 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.

Purpose2/5

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

The description is essentially the tool's title restated ('Online World Model Training Step') and names no verb beyond 'training step'. It does not distinguish this tool from the many wm_* siblings (wm_encode, wm_predict, wm_plan, wm_status, wm_surprise). An agent cannot tell what operation is actually performed or on what.

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

Usage Guidelines1/5

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

There is no when-to-use guidance, no prerequisites, and no mention of any alternative sibling. With 20+ wm_/snn_/tcai_ tools in the namespace, the agent is left to guess when an online training step is appropriate versus wm_predict or snn_step.

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

Deploy Server