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

readOnlyHint=true already covers the safety profile, and the description adds genuinely new behavioral context: the HTTP endpoint (POST /minfraud/v2.0/factors) and, notably, the extra response content (risk_score_reasons, per-factor subscores) that no output schema documents. It omits auth requirements, rate limits, and pricing/billing tier for these calls, which keeps it out of the top band.

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 short sentences, front-loaded with the differentiating claim, then the request-body equivalence, then the raw endpoint. No filler or restatement of the title, and the final sentence earns its place as an implementation detail.

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 11 nested parameters, 0 required fields, low schema coverage and no output schema, an agent needs more than this to call the tool confidently — it cannot tell which fields are actually needed for a score. The description partially compensates by describing what comes back, but the input contract remains largely undisclosed.

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 only 18% across 11 top-level parameters, so the description carries the burden — and it explains no parameters at all, deferring entirely with 'Same request body as minfraud_score'. That delegation only helps an agent that already knows the sibling's contract; nothing clarifies the nested device, order, or custom_inputs fields.

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?

States a specific verb-and-resource framing — 'the most detailed assessment' — and defines it as a strict superset of a named sibling ('everything in Insights PLUS risk_score_reasons and per-factor subscores'). This lets an agent rank it against minfraud_insights and minfraud_score without opening any schema.

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 tiering language ('most detailed', 'PLUS... explaining WHY the score is') and 'Same request body as minfraud_score' tell the agent when this is the right choice versus the cheaper siblings. It stops short of an explicit exclusion ('do not use when you only need the score'), so it is context rather than a full decision rule.

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