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

Annotations already establish read-only, open-world, and idempotent behavior, lowering the burden. The description adds meaningful behavioral context: the async requirement to avoid timeouts, the fact that it returns status/warnings/source references, and that it is a risk assessment tool. No contradictions with annotations, and the added details enhance transparency beyond the structured fields.

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?

The description is three sentences with no filler. The first sentence states the core purpose, the second adds audience and outputs, and the third gives a critical operational requirement. Every sentence earns its place, and the structure is front-loaded with the primary function.

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?

Given the presence of an output schema and strong annotations, the description does not need to explain every return value, but it still mentions status, warnings, and source references, which is helpful. It covers the tool's purpose, target audience, inputs, async behavior, and output highlights. It could be slightly more explicit about how to use the results or edge cases, but it is largely complete for its complexity.

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 100%, so parameters are already well-documented. The description adds value by explaining that the tool 'accepts model outputs or decision boundaries' (clarifying modelOutput) and explicitly notes the async requirement, which gives pragmatic meaning to the async parameter. This exceeds the baseline but does not fully elaborate on edge-case usage.

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 description clearly states a specific verb+resource: 'evaluates AI model resilience against adversarial inputs' and further distinguishes itself by referencing NIST AI RMF red-teaming protocols, structured risk scores, failure modes, and adversarial examples. It effectively differentiates from sibling tools like jailbreak_attempt_detector or model_behavior_drift_monitor by emphasizing proactive stress-testing and risk assessment.

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?

The description provides clear context for use: it is designed for security and compliance personas and accepts model outputs or decision boundaries, implying when to invoke it. It also gives a concrete operational guideline ('Requires async:true to avoid timeout errors'). However, it does not explicitly name alternatives or state when not to use it, so it stops short of exhaustive guidance.

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