mcp-server-worldquantbrain

by tukorama

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Run submission checks

check_alpha_submission

Read-onlyIdempotent

Run BRAIN pre-submission checks on an alpha ID to receive a PASS, WARNING, FAIL, or PENDING verdict before submission.

Instructions

Run BRAIN's pre-submission checks. verdict is PASS, WARNING, FAIL or PENDING.

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": {
      "alpha_id": "<alpha_id>"
    },
    "name": "check_alpha_submission"
  }
}

Input Schema

Name	Required	Description	Default
`alpha_id`	Yes	BRAIN alpha id, for example 'qMPjAxnO'.
`wait_seconds`	No

Output Schema

Name	Required	Description	Default
`checks`	No
`failed`	No
`pending`	No
`verdict`	Yes
`alpha_id`	Yes
`warnings`	No
`next_step`	No
`correlation_pending`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

B3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the verdict enumeration, but omits the most consequential behavior: that the call can block for up to wait_seconds (default 120, max 900), and whether PENDING means the caller should poll or retry. That blocking/polling semantics is the main behavioral gap worth closing.

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

Conciseness5/5

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

Two short sentences, front-loaded with the action and followed by the result vocabulary. Nothing is padded or redundant given the small surface area.

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?

An output schema exists so return values need not be re-explained, but the wait/polling behavior and the preconditions for a valid call are missing for a tool that can hold open for 15 minutes. For an open-world check operation this leaves the agent under-informed about timing and retry strategy.

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

Parameters2/5

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

Schema coverage is 50%: alpha_id has an example in the schema, but wait_seconds carries no description anywhere. The definition never mentions the wait parameter, its default, or that 0 means fire-and-forget, so the description does not compensate for the uncovered parameter.

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 gives a specific verb plus resource -- running BRAIN's pre-submission checks -- which is concrete enough to distinguish it from read-oriented siblings like get_alpha or list_alphas. It stops short of naming what it checks (e.g. before simulation or production use), so the scope is slightly under-specified.

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 guidance on when to call this versus other validation-adjacent tools such as get_simulation_status, nor any stated prerequisites like needing a completed simulation or an authenticated session. An agent must infer the preconditions entirely from the tool name.

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