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

With no annotations provided, the description carries the full burden and does substantial work: it discloses that hard blocks are never averaged away, that billing is per component with cached components refunded, and that the exact figure is reported as billable_lookups. It omits details like authentication, rate limits, and empty-input behavior, but the disclosed cost and aggregation semantics are genuinely useful.

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 four sentences: it front-loads purpose and output, then presents behavioral and cost context, with no filler. The prose is dense but efficient, and the billing condition earns its place because it affects how an agent predicts cost.

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 main output, hard-block behavior, and billing model, which is strong for a scoring tool. However, with no output schema and no annotations, it leaves strictness unexplained, contradicts itself on domain support, and says nothing about calling it with no identifiers. These gaps prevent it from being fully self-sufficient.

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 20% (phone_country), so the description must compensate, but it does not explain strictness or resolve the missing 'domain' parameter. It mentions IP, email, phone, and domain as combinable components, yet the schema contains no domain field, and strictness's range or effect is left undocumented. The per-component cost note adds some meaning but does not compensate for the low coverage and mismatch.

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 clear verb and resource ('Score an entire signup in one call') and describes the returned artifacts: a single weighted risk score, a verdict, and top contributing signals. It also distinguishes itself from sibling per-value tools with 'This is the tool to use when judging a person rather than a value.' However, it claims 'domain' is a component while the input schema has no domain property, which slightly muddies the stated scope.

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 'This is the tool to use when judging a person rather than a value' gives an explicit selection heuristic compared to single-value sibling tools, and 'any combination' communicates the aggregate use case. It does not explicitly name siblings or list exclusion conditions, so it stops short of a 5.

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