ASTRA

wm_predict

Predict next spiking neural network (SNN) states in latent space from spike-injection actions, supporting conditioned multi-step rollouts.

Instructions

Predict Next SNN State in Latent Space

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_predict"
  }
}

Input Schema

Name	Required	Description	Default
`steps`	No	Number of prediction steps (rollout)
`action`	Yes	Spike injection action to condition prediction on

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

C2.5/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds nothing on top of that: it does not say whether prediction mutates latent state, what the conditioning action does internally, or what is returned — despite a prediction tool whose readOnlyHint=false is itself non-obvious.

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

Conciseness3/5

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

The description is a single short fragment with zero padding, so nothing is wasted on verbosity. However, that brevity comes from under-specification rather than disciplined concision, and the fragment is not even a full sentence.

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?

This is a complex tool with a nested action object and no output schema, and the annotations raise a question (why is a 'predict' operation not read-only?) that the description never addresses. For a latent world-model step embedded among many wm_* siblings, the definition leaves too much for the agent to infer.

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%, so 'steps' (rollout), 'action.targetNeurons', 'action.strengths [mV]', and 'action.duration' are already fully documented. The description contributes no parameter meaning beyond the schema, which is exactly the baseline-3 case when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

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

The phrase names a verb ('Predict') and a resource ('Next SNN State in Latent Space'), so the broad intent is discernible. But it is a title-like fragment rather than a statement of what the tool does, and it draws no boundary against the dense wm_* sibling family (wm_plan, wm_encode, wm_surprise, wm_train_step), leaving an agent unable to tell these apart.

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?

There is no when-to-use guidance, no prerequisites, and no alternatives named despite four sibling world-model tools that could plausibly be chosen instead. The description is entirely silent on the conditions that select this tool.

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

Deploy Server