Nimbus BCI

EEG Stream Telemetry

stream.telemetry

Read-onlyIdempotent

Live snapshot of a streaming session: latest prediction + recent window, signal quality (meanChannelQuality, snrDb, artifactProbability), indicators, running stats. Poll this while a session runs. Works with OR without a deployed model: modelless hardware streams (no classifier) report live signal quality + focus/relaxation band-power indicators with latestPrediction null; deployed sessions additionally carry predictions and confidence stats. Expect low confidence during filter/ASR warm-up (first seconds); quality < 0.5 or high artifactProbability means the signal is poor. 404 => session not active in this backend. Each poll also feeds the idle watchdog (see stream.start's idle_timeout_sec), keeping an actively watched session alive.

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": {
      "session_id": "<session_id>"
    },
    "name": "stream.telemetry"
  }
}

Input Schema

Name	Required	Description	Default
`window`	No	How many recent predictions/chunks to include (default 50).
`session_id`	Yes	The streaming session to read telemetry for.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 5, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already declare this a safe read, and the description goes well beyond them: it discloses that each poll resets the idle watchdog (a non-obvious side effect for a read-only tool), that confidence is depressed during filter/ASR warm-up, that quality < 0.5 or high artifactProbability indicates a bad signal, and that latestPrediction is null for modelless streams. That is exactly the behavioral context an agent cannot get from structured fields.

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 purpose and the poll instruction are front-loaded, and nearly every clause carries operational value. It is somewhat dense and run-on, with enumerated fields and caveats packed into one paragraph, but little is genuinely redundant.

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 polling telemetry tool, the agent knows what it gets back, how to read the quality metrics, what null predictions mean, what a 404 signals, and that polling has a keep-alive effect. An output schema exists, so the description did not need to enumerate return values yet still covers the interpretation guidance that a schema cannot.

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 both parameters are already documented in the input schema. The description mentions 'recent window' only in passing and adds no semantics about how window size affects cost or response size. Baseline 3 is appropriate when the schema already does 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 opening clause gives a specific verb and resource: 'Live snapshot of a streaming session,' and enumerates the contents (prediction, window, signal quality, indicators, stats). It clearly separates the modelless case from the deployed-model case. It does not explicitly contrast itself with the sibling stream.status, which is the one plausible ambiguity an agent could still have.

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

Usage Guidelines4/5

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

'Poll this while a session runs' gives the operative when-to-use condition, and the 404 note tells the agent what an inactive session looks like. It does not say when to prefer stream.status or stream.stop instead, and gives no polling cadence guidance beyond the implicit 'keep polling'.

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.