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

Goes well beyond the annotations by disclosing fixed simulation assumptions (10,000 capital, 10 bps fees, 1 bp slippage, next-bar-open fills), the absence of daily-test/history caps, and the exact shape of the acceptance receipt including run ids and poll_after_seconds. It also explains the idempotency mechanism more precisely than the idempotentHint annotation alone.

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

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

Core purpose is front-loaded and most sentences earn their place by covering scope, fixed simulation defaults, receipt output, and idempotency. At eight sentences it is on the long side and the 'sandbox validation, supported markets, timeframes and date rules' clause is compressed to the point of being vague.

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

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

For an asynchronous job tool with an output schema, it covers the operationally critical points: idempotent recovery, the polling interval, and the fixed backtest assumptions. The one gap is that date-rule semantics for start_date/end_date are only alluded to rather than explained, which matters given the strict date pattern in the schema.

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

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

Schema coverage is only 20% (request_key is the sole documented property), so the description must carry weight; it does clarify that an exact saved revision is required and that identical request_key plus inputs form the idempotent identity. It adds little on start_date/end_date beyond a vague reference to 'date rules' and nothing on strategy_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (queue a backtest) and resource (any saved strategy plus a matched buy-and-hold baseline), and scopes it to the connected workspace. It is clearly distinguishable from siblings like create_strategy, get_run_report and get_run_data.

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

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

Gives prerequisites (exact saved revision required, accepts custom code and existing app strategies) and implies the follow-up path via the poll_after_seconds status check. It never explicitly names an alternative tool or a when-not condition, so it falls short of full routing guidance.

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