Preview a take

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

readOnlyHint=true is consistent with 'without betting', and the description goes beyond it by explaining the downstream mechanics: compilation into a verifiable rule, Chainlink CRE checking match data, and an AI-judge fallback for takes no data rule fits. It does not say whether the preview is persisted or costs anything, so not a 5.

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 sentences, the read-only/no-bet constraint front-loaded, and the second sentence doing real work by explaining how the rule gets settled. No filler or repetition of the name.

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?

With no output schema, the description should say what a preview returns — the compiled rule text, whether it is machine-checkable, or a rejection reason — because that is the entire value of a preview call. It covers the settlement path but not the response shape.

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 100%, so both parameters (take, match) are already documented in the schema, including the plain-words example and the terrace_matches reference. The description adds no format or constraint detail beyond that, which is the baseline case.

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 and resource: turn a take into a settlement rule and preview it, with 'without betting' distinguishing it from the mutating siblings like terrace_challenge. The Chainlink CRE / AI-judge sentences clarify what the produced rule actually is, so an agent can tell this apart from challenge-creation tools without opening a schema.

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?

'Without betting' implies this is the pre-flight check before terrace_challenge, but no sibling is named and no explicit when/when-not is given. The usage is inferable rather than stated, which is the definition of implied guidance.

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