Nimbus BCI

Start Protocol Assignment

protocol.start_assignment

Enroll a subject and prepare their neurofeedback deploy session (confirm-gated — a session runs on a human). Creates the assignment (yoked sham arms REQUIRE yoked_donor_upload_id: a recorded simulated session's upload — mint one by running an active-arm session and data.upload-ing its recording), then persists the protocol graph as a deployable execution. Requires a Pro plan for LIVE hardware sessions; simulated-source sessions (the default template) are free.

Graph source: execution_id reuses THAT run's stored graph (it must contain a protocol_session node; no device is pre-connected — the deploy session's data source stays yours). Without execution_id the built-in template graph is cloned — simulated source → bandpass → bandpower_indicator → protocol_session stamped with the protocol refs — and a simulated device is connected to the returned session id.

The session starts when a client opens {statusUrl} (the deploy WS), sends init_deployment with modelExecutionId={executionId}, then start; the Studio app shows the feedback panel automatically. Poll protocol.session_status; stop with protocol.stop (the recording's block annotations + assignment progression are written on stop).

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": {
      "protocol_id": "<protocol_id>",
      "protocol_version": "<protocol_version>",
      "subject_label": "<subject_label>",
      "arm": "<arm>"
    },
    "name": "protocol.start_assignment"
  }
}

Input Schema

Name	Required	Description
`arm`	Yes	active \| sham.
`confirm`	No	MUST be true — explicit go-ahead for a session on a human.
`protocol_id`	Yes	Saved protocol id (protocol.save).
`execution_id`	No	Optional completed execution whose stored graph carries a protocol_session node; default clones the template.
`subject_label`	Yes	Subject identifier (e.g. "S01").
`protocol_version`	Yes	Immutable version the assignment pins.
`yoked_donor_upload_id`	No	Donor recording upload (required when the arm's blocks resolve to yoked — the backend validates coverage).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026

removedInput schema / properties / name

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Optional display name for the prepared run."
-}

AddedOct 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-idempotent, open-world, non-destructive write; the description adds the confirm gate, plan gating, the yoked-donor validation the backend performs, and what side effects occur on stop (block annotations and assignment progression are written). It also discloses that a simulated device is auto-connected only in the template path and that no device is pre-connected when reusing an execution graph — none of which is in the annotations.

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?

The intent is front-loaded in the first sentence and every paragraph carries real information, but the parenthetical nesting is heavy and the deploy-WS handshake paragraph reads more like runbook steps than tool contract. Slightly denser than needed for a single tool, though not padded.

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

Completeness5/5

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

For a 7-parameter, gated, stateful tool this covers requirements, the two graph-source paths, the arm/donor interaction, and the post-call session lifecycle. An output schema exists, so the description is not obliged to explain return values, and it still tells the agent to poll protocol.session_status and stop via protocol.stop.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds genuinely non-obvious meaning: how to mint a yoked_donor_upload_id (run an active-arm session and data.upload its recording), what execution_id must structurally contain (a protocol_session node), and that confirm is a mandatory safety gate rather than a flag. Only protocol_version and subject_label are left to the schema alone.

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

Purpose5/5

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

"Enroll a subject and prepare their neurofeedback deploy session" gives a specific verb and resource, and the description ties it to the surrounding workflow (protocol.save for the protocol, protocol.session_status to poll, protocol.stop to end). An agent can distinguish this from execution.run or protocol.save without opening any schema.

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

Usage Guidelines5/5

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

Usage conditions are spelled out in detail: confirm must be true because a session runs on a human, LIVE hardware needs a Pro plan while simulated-source sessions are free, yoked arms require a donor upload id, and execution_id vs. template graph is an explicit either/or. It also states the two lifecycle prerequisites (client opens statusUrl, sends init_deployment then start) that must hold for the assignment to actually run.

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

All Nimbus BCI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.