Skip to main content
Glama
Sign In

Nimbus BCI

by io.github.nimbusbci
OverviewDiscussionsAdmin

Leaderboard

catalog.leaderboard
Read-onlyIdempotent

Public benchmark leaderboard: pipeline rankings per dataset.

Two tracks: the top-level within_session block (curated suite pipelines) and crossSubject (leave-one-subject-out — curated pipelines plus BYO python_model submissions; BYO rows carry kind: "byo" and an owner name). Within each dataset, rows sort desc by meanAccuracyPct (95% CI in ciLoPct/ciHiPct). packFingerprint identifies the exact dataset pack behind the scores; updated marks each dataset's most recent run. The pretrainedFewTrial efficiency track means: accuracy at a protocol-fixed 100-trials-per-subject budget — the frozen-backbone / few-parameter rows that matter when calibration data is scarce (paramsTrained shown per row so cost is readable next to accuracy). submittableDatasets is the set open for leaderboard.submit; a dataset can appear under crossSubject and still be closed for new submissions.

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": "catalog.leaderboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataset_idNoOptional dataset id. When set, every track is filtered to that dataset. Omit it for the full board.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / dataset_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional dataset id. When set, every track is filtered\nto that dataset. Omit it for the full board."
+}
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, so safety is covered; the description instead adds domain semantics that annotations cannot express — track meanings, row sort order, CI fields, packFingerprint stability, and the pretrainedFewTrial budget definition. It does not mention pagination or auth, but for a public read board that is minor.

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 purpose is front-loaded in one line, but the body is a dense paragraph of return-value documentation that partly duplicates what the output schema already conveys. Terminology such as crossSubject, packFingerprint, and pretrainedFewTrial is packed into consecutive clauses without structure, making it slower to scan than necessary.

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

Completeness4/5

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

For a one-optional-parameter read tool with an output schema and full annotation coverage, the definition is complete — an agent can call it correctly and understand every field it will see. Some of the return-field explanation is redundant with the output schema, which is the only thing keeping it from a 5.

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 100% and the single dataset_id parameter is already documented with the same filtering semantics the description implies. The description adds adjacent context (a dataset can appear under crossSubject yet be closed for submissions), but adds no format or id-syntax detail beyond the schema, so the baseline 3 applies.

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 line states a specific resource and scope: 'Public benchmark leaderboard: pipeline rankings per dataset.' The rest of the description names the contents (within_session vs crossSubject tracks, BYO rows), so an agent knows exactly what it gets back. It does not explicitly distinguish itself from sibling readers such as leaderboard.mine or leaderboard.status, which keeps it out of 5 territory.

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

Usage Guidelines3/5

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

Guidance is limited to parameter behavior ('Omit it for the full board') and an indirect pointer that submittableDatasets is the set open for leaderboard.submit. There is no explicit statement of when to call this versus leaderboard.mine or leaderboard.status, so usage is implied rather than stated.

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

All Nimbus BCI toolsInspect
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.

Resources