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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds substantial context on top: the passive mechanism (public DNS delegation checks plus public CT-log queries), the safety implication ('sends nothing to the target... safe and lawful to run'), the operational constraint of rate-limiting, the no-API-key requirement, and the critical NEUTRAL FRAMING caveat that lookalikes must be reported as exposure to verify, never as an accusation. This goes well beyond what the 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 front-loaded with the core purpose and the most important caveat (NEUTRAL FRAMING) early, and every paragraph earns its place: criteria, interpretation warning, passivity rationale, sibling routing, and operational constraints. It is slightly verbose — 'PASSIVELY' in caps is restated as 'Fully passive' later, and 'Read-only' repeats the readOnlyHint annotation — but the density of genuinely useful information justifies the length.

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 tool with one fully-documented parameter, a rich annotation set, and an output schema, the description is remarkably complete: it covers the assessment criteria, the grading scale, the interpretive framing, the operational mechanism, rate limits, the API-key requirement, sibling routing, and even summarizes the return format (grade, counts, per-category findings, shareable link). Nothing an agent needs to invoke it correctly is missing.

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%, and the single 'domain' parameter is already fully documented in the schema ('Registrable domain... Scheme and path are stripped.'). The description's repeated use of 'domain' adds no meaning beyond what the schema provides, so the baseline of 3 applies — the schema carries the semantic weight here.

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 opens with a specific verb-resource pair ('Assess how exposed a domain is to brand impersonation and phishing') and enumerates concrete criteria: live typosquat/lookalike domains, operational subdomains in CT logs, and wildcard certificate existence, with an A+ to F grading scale. It differentiates from siblings by explicitly naming lookalike_domains and subdomain_discovery as the raw-detail alternatives, so an agent can tell them apart without opening schemas.

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 explicitly routes the agent to alternatives: 'Use lookalike_domains or subdomain_discovery for the raw per-tool detail,' establishing a clear boundary between this aggregate-grade tool and its raw-detail siblings. However, the positive case ('use this tool when you want an overall exposure grade') is implied by the framing rather than stated outright, so the when-to-use-this condition is left slightly to inference.

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