ASTRA

np_closed_loop

Destructive

Reads organoid activity, couples it to ASTRA fusion, ROS, and ethics monitoring, and optionally injects active electrodes as spikes to drive the SNN for closed-loop bio-hybrid control.

Instructions

NeuroPlatform v2 — Closed loop: read organoid → couple to ASTRA fusion/ROS/ethics, optionally drive the SNN

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": "np_closed_loop"
  }
}

Input Schema

Name	Required	Description
`drive_snn`	No	Inject organoid-active electrodes as spikes into the ASTRA SNN
`window_ms`	No
`couple_ethics`	No	Mirror organoid viability into the IRB ethics gateway (eth.viab)
`drive_strength`	No	Spike injection strength (mV) when drive_snn=true

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.1.0Sep 23, 2026

TDQS

C2.9/5.0

Behavior2/5

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

Annotations declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the agent knows this mutates state, but the description frames the operation as 'read organoid → couple' and never discloses what is destroyed or that effects are non-reversible. It adds coupling detail (ROS/ethics, optional SNN drive) but leaves the destructive consequence that the annotations flag unexplained.

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?

It is a single arrow-chained line that is front-loaded and free of padding. However, the telegraphic phrasing is compact at the cost of readability, which limits how much structure it actually provides.

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?

For a multi-step coupling pipeline with four parameters, a destructive mutation hint, and no output schema, the one-line description is too thin. It never explains return values, what 'couple to ethics' writes, or the effect of window_ms, so an agent cannot fully predict the call's outcome.

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 coverage is 75%, so most parameters are already documented in-schema. The description only clarifies the conditional gating of drive_snn and adds no detail about window_ms or drive_strength semantics. Baseline 3 is warranted when the schema does most of the work.

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 compound operation: reading an organoid, coupling it to ASTRA fusion/ROS/ethics, and optionally driving the SNN. The verb chain is clear enough to distinguish it from read-only status siblings like get_snn_state or check_ethics, but it leans on platform jargon (ASTRA, ROS, IRB ethics gateway) and never explicitly contrasts it with the closer siblings.

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 named alternative. The word 'optionally' and the link to the drive_snn parameter hint at behavior but do not tell an agent when this closed-loop tool should be chosen over snn_step, inject_spikes, or check_ethics. Usage is only obliquely implied.

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

Deploy Server