Evaluate decision questions

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

Adds genuine context beyond annotations: it states the response is synchronous structured decisions and that a decision does not authorize an external action. However it leaves the non-obvious readOnlyHint=false and idempotentHint=false flags unexplained (side effects, state mutation), so the behavioral profile is only partially clarified.

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?

Four short, front-loaded sentences that each carry a distinct point (purpose, prerequisite, return shape, safety note). Efficient with no obvious filler.

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?

Covers the return shape well in absence of an output schema and states the discovery prerequisite, but for a 4-parameter nested-object tool with 25% schema coverage it leaves the input formats under-specified.

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 only 25% and the schema has nested objects, so the description must compensate. It gives semantic grounding ('questions' are typed probability/Choice/Score, 'state' is shared, 'model' comes from discovery), but does not explain formats for model or state, leaving gaps.

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 ('Evaluate') and resource ('typed Noul probability, Choice, and Score questions against shared state'), which is enough to distinguish it from the surrounding model/pricing/chat siblings. The jargon ('Noul', 'System One endpoint') blurs it slightly but the core purpose is clear.

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 prescribes a prerequisite flow: 'Discover a decision model with list_models/get_model first', naming the alternative tools. It also contrasts with chat tools ('not chat text'), though it never states when-not to use it.

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