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

Annotations already declare readOnly/idempotent/closed-world, so the bar is lower, and the description adds real behavioral context: the two-mode behavior, the shape of the output (0-100 residual score, risk level, red flags, missing controls with OWASP/GDPR/AI Act references), and the caveat that results are self-reported rather than measured. It stops short of covering validation behavior for malformed or partial answer keys, which is the remaining gap.

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?

Three sentences, front-loaded with the trigger condition, then the two modes, then the limitation. No sentence restates the title or the schema; each adds decision-relevant 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?

With no output schema, the description carries the return-value burden and does so: it names the question counts, the 0-100 score with direction ('0 = lowest'), the risk level, red flags and remediation references. Combined with the closed-world annotations and a fully documented single parameter, an agent has everything needed to call it correctly.

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 baseline is 3; however the description adds meaning the schema does not — that omitting `answers` entirely is a legitimate discovery mode returning the question set, and that the answer universe spans 9 exposure and 11 control questions. That framing turns an optional object parameter into an understood control flow.

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 states a specific verb and resource — assessing how risky an AI agent/assistant setup is — and anchors it with concrete user phrasings ('is it safe to let our agent read email and send replies?'). It also carves out what the tool is not ('a self-assessment ... not a scan or test'), which separates it from the many assessment siblings such as cyber_risk_score or vendor_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?

It gives explicit when-to-use triggers via example questions and defines two distinct invocation modes: no answers returns the 9 exposure + 11 control questions, with answers returns the scored result. The negation clause steers the agent away from treating this as a technical scan, which is the closest competing interpretation.

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