check

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

With no annotations, the description itself explains the output contract (answer, probability of yes, calibrated confidence) and implies a read-only evaluation of state. It does not disclose model-selection behavior, errors, or side effects, but for a query-style tool the main behavior is captured.

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 front-load the core behavior, then add return details and two illustrative examples. No fluff or repeated schema 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?

Output schema covers return values, but the description lacks guidance on the model parameter, the meaning of 'noul gate', and how to choose check over decide/classify/triage. It is not complete enough on its own for reliable invocation.

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 0%, so the description must compensate. It clarifies that state is the thing being evaluated and instructions are the yes/no question, but it never explains the optional model parameter or the expected format of instructions, leaving a real 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?

The opening sentence names a specific verb ('Answer'), a single decision type ('yes/no/unknown'), and a target resource ('a state / noul gate'), with concrete control-flow examples. This is enough to separate it from siblings like classify, score, and decide even though no sibling is named.

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?

'Ideal for agent control flow' plus the refund/security examples gives a clear when-to-use context for binary gating questions. It does not name alternatives or exclusions, so it stops short of the highest level.

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