Fraud triage

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

The description adds an important side effect not captured by the annotations: 'Costs credits from the account wallet.' It also frames the output as advisory checks rather than executed actions. This meaningfully supplements the readOnlyHint, openWorldHint, and destructiveHint annotations, though it does not cover auth/rate-limit details.

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 short sentences carry the entire payload: input, output, use context, and cost. The arrow-based formulation is front-loaded and efficient, with no filler or repetition of the tool name/title.

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?

The description covers the input, expected outputs (risk score, signals, checks), the pre-shipment context, and the cost implication. With only two parameters and no output schema, this is largely sufficient, though it does not spell out response format or edge cases around insufficient credits.

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%, and the schema already documents that `order` can include whatever data is available and `context` carries store-level patterns. The description only restates 'an order or transaction in context' conceptually and does not add field-level detail 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 clearly states the core transformation: an order/transaction plus context produces a risk score, the signals behind it, and checks to run before shipping. It is specific enough to distinguish fraud triage from general parsing tools, though it lacks an explicit verb and does not directly contrast with nearby siblings like parserail_chargeback.

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 phrase 'before you ship' gives a clear timing/context cue, implying this is for pre-shipment fraud triage. However, it does not name alternatives or state when not to use the tool, and with many similar siblings in the list, an agent must infer the selection boundary.

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