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

Annotations already mark the tool read-only, idempotent, and non-destructive; the description adds meaningful context beyond those: it calls SEON, aggregates multiple signals, and returns fraud_score, applied_rules, and a decision state such as APPROVE/REVIEW/DECLINE. It also communicates the minimum accepted input. 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?

Two purposeful sentences plus a compact example. The main capability and input requirement are front-loaded, and there is no filler or redundant restatement of schema fields.

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?

Even with no output schema, the description tells the agent what the response contains: fraud_score, applied_rules, and decision state. Combined with full parameter documentation, annotations, and a realistic example, an agent has enough information to select and invoke the tool 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 the baseline is 3. The description adds value by expressing the grouping constraint that at least one of email/phone/ip must be provided, which is not obvious from individually-optional schema properties. The example also demonstrates how the parameters fit together in practice.

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: 'Aggregate fraud assessment via SEON'. Clearly distinguishes from the single-signal sibling tools (seon_email, seon_ip, seon_phone) by saying it combines email, phone, and/or IP into a single fraud_score with applied_rules and a decision state.

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?

States the core precondition clearly: 'Pass at least one of email/phone/ip', and gives a concrete invocation example. It implies the aggregate-vs-single-tool distinction through 'combine ... into a single fraud_score', but it does not explicitly say when to prefer this tool over the seon_* siblings or when those are more appropriate.

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