mcp-server-worldquantbrain

Overview Schema Source Related Servers Discussions Admin

Simulate several alphas

simulate_alphas_batch

Backtest up to 30 FASTEXPR alphas in BRAIN batches, grouping by delay and region. It skips expressions already in the ledger and returns not_started items for later resubmission.

Instructions

Backtest up to 30 expressions, sent to BRAIN in groups of at most 10.

All expressions must share one delay; different regions are sent as separate groups.
Multi-simulation needs a Consultant account. Expressions already in the ledger are returned
without spending quota. not_started lists anything that could not be sent; resubmit those later.

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": {
      "alphas": "<alphas>"
    },
    "name": "simulate_alphas_batch"
  }
}

Input Schema

Name	Required	Description
`wait`	No	True blocks until done or timeout; False returns the id at once.
`force`	No	Run again even if the ledger has this exact alpha.
`alphas`	Yes
`timeout_seconds`	No	Seconds to block. Empty uses WQB_SIMULATION_TIMEOUT.

Output Schema

Name	Required	Description	Default
`status`	Yes
`message`	No
`results`	No
`batch_ids`	No
`next_step`	No
`not_started`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Adds substantial behavior beyond the annotations: grouping semantics (max 10 per request), the shared-delay precondition, an account-tier prerequisite, quota-preserving ledger dedupe, and the existence of a 'not_started' bucket for partial failures. What it does not disclose is the partial-failure semantics in more depth (e.g. whether already-sent groups are charged when a later group fails) or the blocking/timeout tradeoff, though the schema covers the latter.

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?

Four short sentences, each carrying a distinct operational fact (scale cap, grouping constraint, account/quota behavior, failure handling). Front-loaded with the core action, no filler, no restatement of the title.

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?

With an output schema present, the description need not document return values, and it wisely spends its words on preconditions instead. Given the non-idempotent, open-world nature of the call, it is nearly complete; the main residual gap is failure/charge semantics when only some groups succeed.

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 75%, so the baseline is already partially carried by the schema. The description still earns credit by documenting a cross-parameter constraint the schema cannot express: every AlphaSpec must share one delay, and region differences force separate batches. The 'force'/'wait'/'timeout_seconds' behavior is left entirely to the schema text.

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?

States a concrete verb and resource ('Backtest up to 30 expressions, sent to BRAIN') with the batch size cap and internal chunking of 10, which makes the batch nature unambiguous against a single-simulation sibling. It never names the single-alpha alternative, so differentiation is implied by scale rather than stated.

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?

Gives real conditions: all expressions must share one delay, regions are split into separate groups, and multi-simulation requires a Consultant account. It also explains the ledger short-circuit and what to do with 'not_started' (resubmit later). It lacks an explicit 'use this instead of X when...' comparison and says nothing about when 'force' or 'wait=false' should be preferred, but those live in the schema.

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