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

Annotations already supply read-only and non-destructive hints, and the description goes beyond them by disclosing that this is a paid call priced at $0.10 USDC via x402, and that it is a one-call bundle rather than separate lookups. It also reveals the component data sources (SPF/DMARC, redirects, domain age, hosting, IP reputation). This is useful operational context beyond what annotations convey.

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 compact and well ordered: output first, then what is fused, then intended agent use, then price. Every sentence carries useful selection or invocation information and no text is redundant with the schema. It is appropriately front-loaded for an agent scanning many tool listings.

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 single-paid-call tool with no output schema, the description provides sufficient context: expected inputs, what the tool analyzes, the return value (verdict + risk score), the intended use case, and cost. There is no critical missing information that would prevent an agent from selecting and invoking the tool correctly. The lack of explicit alternatives is minor here because the intended workflow is clearly stated.

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?

The schema description covers 100% of the parameters (email, url, ip), so the structured data already does the heavy lifting. The description adds only a loose mapping: 'sender-domain authentication' relates to email, 'destination-link safety' to url, and 'optional source-IP reputation' to ip. That is helpful orientation but not format-level semantics beyond the schema, so the 3 baseline applies.

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 exactly what the tool does: it returns a SAFE/SUSPICIOUS/PHISHING verdict plus 0-100 risk for an inbound message by fusing sender-domain, link-safety, and IP-reputation signals. The 'bundle' framing and the mention of fused signals distinguish it from the many single-signal sibling tools like email_sender_trust, url_safety, and threat_ip. The target use case ('screening inbound email, DMs and leads') makes its purpose unmistakable.

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 a clear context for use: agents screening inbound messages before acting on them. It does not explicitly say when not to use it or name alternatives such as using individual email/URL/IP checks instead, but the broad use case is enough to guide an agent. A small deduction for lacking explicit exclusions or alternative-tool routing.

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