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

With no annotations at all, the description carries the full burden, and it does disclose genuinely useful traits: no cost, no latency, and no signature/commitment side effect, implying a non-mutating simulation. It does not say whether anything is persisted, what the response contains, or that results are in-sample fits over history, which the phrase "a rule can be fitted to history" only vaguely gestures at.

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?

Two short sentences with no padding, which is appropriately sized. However, the wording is aphoristic rather than front-loaded with a clear action and object, so the reader must decode slogans ("against a coin flip," "fitted to history") before understanding the tool.

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?

A 12-parameter simulation tool with no annotations and no output schema needs the description to explain both behavior and what comes back, and this one explains neither. Critically, it never says the result is a performance comparison against a random baseline, which is the key thing an agent must interpret when reading the response.

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?

With 12 parameters at 67% schema description coverage, the description adds almost nothing beyond the schema: "after its costs" hints fees are modeled, but stopLossPct, takeProfitPct, maxHoldHours, side, and market semantics are left entirely to the schema. Undocumented fields like stopLossPct and takeProfitPct receive no explanation in either place, so the description does not compensate for the coverage gap.

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?

"A rule on the recent past of any market the lab reads, against a coin flip, after its costs" obliquely conveys a historical backtest of a hypothetical trading rule benchmarked against a random 50/50 baseline net of fees, but it never uses a verb like preview, backtest, or simulate and never states what the tool produces. The contrast with the sibling opsin_perp_propose is only hinted at through "never signed," so an agent must infer that this is the unsigned dry-run counterpart.

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?

"Free, instant and never signed" implicitly tells the agent to try a rule here before committing it via a propose/sign path, which is real when-to-use signal. There is no explicit statement of when not to use it, no mention of opsin_perp_propose or opsin_market_preview as alternatives, and no prerequisites such as needing to read opsin_perps first.

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