Skip to main content
Glama

script_rehearse

Read-onlyIdempotent

Step a cubicle.script v1 over the deck's own bars with the deterministic reference runner (cubicle-script run): one frame per bar (state, every gate's truth and the two sides it compared, fields, vars, position, order, fill, log), the summary (trades, wins, sum R, final state, blocked counts) and the frame hash — the run's receipt. Same script, params and window → the same hash (cached). Window defaults: the previous weekday's cash session (13:30–20:00 UTC) for NQ/ES, the last sealed 8 h for BTC/ETH/SOL; at most 6,000 bars. Pass script (YAML) or example (ny-open-breakout, range-aware-stop); params replaces defaults within min..max and changes the hash. Metered on the run, not the bars.

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": "script_rehearse"
  }
}

Input Schema

NameRequiredDescriptionDefault
tfNodefault 1m
toNounix seconds (in the past)
fromNounix seconds; with `to`, an explicit sealed window
hoursNocrypto only: the last N sealed hours (default 8)
framesNohow many frames to return from the END of the run (default 60, max 600); the summary covers the whole run
marketNodefault NQ
paramsNoparam overrides {name: number}, clamped to the script's min..max
scriptNothe cubicle.script v1 YAML text (or use example)
exampleNoa bundled example instead of script: ny-open-breakout | range-aware-stop

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / example / description
      Previous value: -"a bundled example instead of script: bender-corridor | ny-open-breakout | range-aware-stop"New value: +"a bundled example instead of script: ny-open-breakout | range-aware-stop"
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces that with concrete substance: determinism guarantees ('Same script, params and window → the same hash (cached)'), the 6,000-bar ceiling, the per-market default windows, and the fact that billing is per run rather than per bar. It stops short of saying what happens on an invalid script or on min/max clamping failure, which is the main remaining behavioral gap.

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?

Front-loaded with the core action, then progressively narrower detail (output shape, determinism, defaults, limits, metering). It is one dense paragraph with heavy parentheticals that read as jargon, but almost every clause carries information an agent needs.

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 9-parameter, no-output-schema tool, the description effectively documents the return surface — per-bar frames with gate truth and the compared sides, the aggregate summary, and the receipt hash — plus cost and size limits. Only error/failure behavior for malformed YAML or out-of-range traffic is unaddressed.

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 3 is the floor, but the description adds real meaning: `params` replaces defaults and 'changes the hash', the window defaults are spelled out per market/timeframe, and `frames` is scoped as a tail-only view while the summary covers the whole run. That clarifies interaction between parameters in a way the schema alone does not.

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 specific verb and resource — 'Step a cubicle.script v1 over the deck's own bars with the deterministic reference runner' — and names the underlying runner (cubicle-script run). It is clearly a script backtest/rehearsal rather than a validation or a live replay, but it never explicitly contrasts itself with the sibling tools `rehearse` or `script_validate`, so an agent must infer the boundary.

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?

Usage is implied by the operational detail: pass `script` (YAML) or `example`, and window defaults apply if you omit `from`/`to`/`hours`. However there is no explicit 'use this when you want X, use script_validate instead when Y' routing, and no stated preconditions such as validating the script first.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources