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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description discloses critical operational behaviors: it performs no sending, uses a maintained list of ~100k disposable domains, does live MX lookup, and has a cost of $0.001 per call with 10 free/day. These details are not available in the annotations and materially affect invocation decisions, such as cost and safety.

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 three sentences, each serving a distinct purpose: stating the core question and checks, explaining the no-SMTP behavior and rationale, and providing cost information. It is slightly longer than the minimal necessary but contains no filler; the primary purpose is front-loaded. It earns a 4 rather than 5 because the price detail, while useful, could be considered tangential to invocation.

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?

Given the tool has one simple parameter and no output schema, the description covers the essential context: what the tool does, how it operates, its limitations, and its cost. The only gap is that the description mentions a 'verdict' but does not describe the return format or whether detailed breakdowns are provided. This is a minor gap for a check tool but prevents a perfect score.

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 input schema provides only a 'email' string with 0% description coverage. The description fully compensates by clarifying that the parameter is the email address to be evaluated, and it explains the semantics of the check (syntax, MX, disposable, role, free-mail). This gives an agent complete understanding of what the single parameter means.

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 clear question, 'Will this email address work?', and enumerates exactly what is checked (syntax, MX records, disposable/throwaway providers, role addresses, free-mail providers). It also distinguishes the tool from others by explicitly stating it does not send anything and avoids SMTP probing, setting it apart from sibling tools like dns_lookup and domain_whois.

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 provides clear usage context: you would use this tool to assess if an email address is likely deliverable without sending mail. It also explains why SMTP probing is avoided (blacklist risk), implying this tool is safe for bulk validation. However, it does not explicitly name alternatives or state when not to use this tool, so it falls 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.