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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar for behavioral disclosure is lower. The description adds useful behavioral details: all signals are optional, and the output includes a fraud probability, risk level, decision, and per-factor breakdown. No contradiction with annotations.

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 core purpose and input flexibility are front-loaded, and the return structure is clearly laid out. There is minor redundancy between the prose return summary and the 'Returns:' dict-keys list, but the description remains appropriately sized for a tool with 18 parameters.

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?

For a read-only scoring tool with no required parameters and no output schema, the description adequately supplies the return contract and input expectations. It could additionally explain risk_level/decision_bands semantics or point to fraud_feedback, but the provided detail is sufficient for correct 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 100%, so the schema already documents all 18 parameters. The description adds only a general statement that all signals are optional, which is already implied by default nulls. There is no meaningful per-parameter semantic value added beyond the schema.

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 uses a specific verb and resource: 'Score a transaction or account event for fraud risk.' This clearly distinguishes it from the sentiment, toxicity, and PII siblings, and is also obviously different from fraud_feedback, which is about feedback rather than scoring.

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 gives clear usage context: use it when you need a fraud risk score for a transaction or account event. 'Send whatever signals you have — all optional' also tells the agent when it is acceptable to call with partial data. It does not explicitly name alternatives or exclusions, but this is a distinctive tool among the siblings.

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