Skip to main content
Glama

AlgoRover Research

start_backtest

Idempotent

创建个人远端历史回测任务,返回任务标识。

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": {
      "prepared_input": "<prepared_input>",
      "preparation_ticket": "<preparation_ticket>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "start_backtest"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoen
prepared_inputYes
idempotency_keyYes
preparation_ticketYes

Output Schema

NameRequiredDescriptionDefault
dataNo
errorNo
schema_versionNo2.0

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.4/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only that the job runs remotely and returns a task identifier, saying nothing about idempotency-key reuse behavior, cost/quota implications, or what a failed start leaves behind — meaningful gaps for a job-launching mutation.

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?

It is a single front-loaded sentence with no filler and nothing redundant. However, this is brevity achieved through omission rather than efficiency; the one clause present leaves the caller without the workflow context needed to invoke the tool.

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?

For a tool this complex — nested prepared input with digests, a preparation ticket, an idempotency key, and a strict pipeline relationship with prepare_backtest — the description is far too thin. An output schema exists so return values need not be explained, but the prerequisite chain and the meaning of the ticket/idempotency parameters are absent.

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

Parameters1/5

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

Schema description coverage is 0% across four parameters, one of which (prepared_input) is a deeply nested object with digests and market definitions. The description mentions no parameter at all — not preparation_ticket, idempotency_key, locale, or the prepared_input fields — so it compensates for none of the schema's documentation gap.

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 states a concrete verb and resource — 创建 (create) a 远端历史回测任务 (remote historical backtest task) — plus the personal scope and that it returns a task identifier. That is specific enough to distinguish it from read tools like get_backtest or list_backtests, but it never clarifies how it differs from the sibling prepare_backtest, which is the most confusable operation.

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 when-to-use guidance at all. The description does not state that a preparation ticket from prepare_backtest must exist first, nor when an agent should call start_backtest rather than prepare_backtest, despite those being adjacent steps in the same workflow.

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.