ASTRA MCP Server

wm_train_step

Train a world model online by injecting stimulation into target neurons between observations. Specify neuron indices, strengths, and duration to apply the action.

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 observedv2.1.0Sep 6, 2026

TDQS

D1.9/5.0

Behavior1/5

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits, but it offers none. It does not state that this operation modifies the model, what side effects occur, whether it requires a running simulation, or what the observable consequences are. 'Training Step' vaguely implies mutation, but that is not explicit.

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?

The description is undeniably short, but it is under-specified rather than efficiently concise. It is essentially a title fragment that restates the tool name and provides no operational substance, so it does not earn its place as a useful description.

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

Completeness1/5

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

For a tool with a nested parameter object, no annotations, no output schema, and a family of closely related wm_* siblings, this description is completely inadequate. An agent cannot determine what the action object represents, how training is performed, what the return value is, or how this differs from wm_predict or wm_encode.

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 nested 'action' object's properties (targetNeurons, strengths, duration) are individually described in the schema. The tool description adds no additional parameter context, so the baseline score of 3 applies: the schema does the heavy lifting.

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 'Online World Model Training Step' simply restates the tool name in expanded form; it does not state a specific verb or resource. It gives some clue that this relates to training the world model, but it fails to distinguish this tool from siblings like wm_encode, wm_predict, or wm_plan in any meaningful way.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, typical scenarios, or any exclusion criteria, leaving the agent to infer usage entirely from the name and parameter schema.

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