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

Annotations declare readOnlyHint=false, so this is a state-changing operation, but the description doesn't say what state changes or what gets created (a forward test run?). It doesn't mention whether the strategy must be in a particular state, whether the operation is reversible, or what happens to existing forward tests. The philosophical framing crowds out behavioral disclosure.

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?

Three sentences, two of which are aphoristic filler about backtest vs future tuning. The action is stated last, and the philosophical framing could be cut without losing operational information.

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 a state-changing tool with no output schema, the description should explain what promotion does operationally, prerequisites, and likely follow-ups (get_forward_result, check_strategy). None of that is present; the description is conceptually evocative but operationally incomplete.

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 description coverage is 100% and the single id parameter is documented in the schema ('Strategy id, from list_strategies'). The description adds nothing about the id or format, so a baseline 3 is appropriate.

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?

The description says 'Begin evaluating a saved strategy on candles it has never seen,' which conveys the core action but uses metaphor ('candles it has never seen') rather than the domain term forward testing stated in the title. It never names forward testing explicitly, and it doesn't differentiate from siblings like run_backtest or get_forward_result.

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?

The description contrasts backtesting with forward testing conceptually ('A backtest can be tuned until it looks good; the future cannot') but never states when to call this tool vs run_backtest, check_strategy, or get_forward_result. No trigger conditions or exclusions are given.

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