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

Goes well beyond the annotations: discloses engine rules (10 bps per side, close execution, no slippage model, unsupported syntax rejected), the rate limit of 60 backtests/day/client with a quota field, that failures are explicit when the engine refuses, and crucially that the server may retain the submitted script so private strategies should not be sent. That retention notice also explains the non-read-only, non-idempotent annotation profile rather than contradicting it.

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?

Every clause carries real information, but the opening 'PAPER PREVIEW (sealed:false, is_keep:false, paper:true)' is raw internal field syntax that forces the reader to decode jargon before reaching the actual purpose, and the bilingual prose adds friction. The lead should be the verb+resource, not the flag tuple.

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?

An output schema exists so return values need no explanation, and the description still covers scope, cost model, quota, retention risk, and failure behavior. The remaining gap is sibling disambiguation against `backtest_arenascript`, which is the most likely mis-selection.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents the 20,000-character ArenaScript field. The description adds engine-level constraints on what the script may contain ('syntaxe non supportée refusée') but nothing about format or content beyond the schema.

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+resource: backtesting an ArenaScript strategy through the Lab's Rust engine on server OHLCV candles resampled to the declared timeframe. However, it never distinguishes itself from the near-identical sibling `backtest_arenascript`, which an agent will immediately be torn between.

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?

Explicitly scopes itself as a paper preview and names the alternative for a real verdict: 'Not a verdict; for a verdict use get_lab_desktop_handoff.' It still gives no guidance on when to pick this over `backtest_arenascript`, `invent_and_backtest`, or `engine_robustness_check`, so a key routing decision is left open.

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