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

With no annotations, the description carries the full burden, and it does disclose a real lifecycle: immediate hashing (immutability), evaluation against future data, comparison against a coin-flip baseline, and signing on resolution, plus a soft rate limit. It omits whether proposals can be cancelled or amended, what happens to losing rules, and what a call returns.

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?

A single compact sentence with the commitment semantics front-loaded and no filler. The trade-off is that 'against a coin flip' and 'A few a day' are oblique phrasings that cost more clarity than the brevity saves.

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 14-parameter creation tool with no annotations and no output schema, the description should at minimum orient the agent on the required fields and the resolution lifecycle. It gestures at the lifecycle but leaves the parameter surface and return behavior entirely undocumented.

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?

Fourteen parameters at 64% schema coverage, and the description explains none of them. It never mentions side, maxHoldHours, the 'when' condition list, stop/take levels, or funding thresholds, so the unlabeled stopLossPct, takeProfitPct and label fields get no help from prose either.

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 verb+resource pair is concrete: 'Preregister a rule' on a market the lab reads, committed as a hash and later resolved. That tells an agent this creates a forward-looking, verifiable prediction. It does not distinguish itself from opsin_market_propose or opsin_propose, and 'any market' obscures that this is the perp-specific variant.

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?

'Hashed now, measured on what comes next' implies the rule must be registered before the outcome exists (no lookahead), and 'A few a day' implies a rate budget. Neither is stated as an explicit rule, and no sibling alternative is named, so an agent must infer when to pick this over the preview or market-propose tools.

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