verify_emailCheck an email for syntax, MX records, disposable/throwaway providers, role accounts (info@, admin@), homograph lookalikes and domain age. Returns a 0-100 risk score and an allow/review/block verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Full email address | ||
| strictness | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It transparently lists the checks performed and the output format (0-100 risk score, allow/review/block verdict), which significantly clarifies tool behavior. It does not mention side effects or rate limits, but for a read-only verification tool this is less critical.
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 entire description is a single sentence, front-loaded with the primary action and packed with specific checks and output details. Every phrase contributes value, achieving high information density without redundancy.
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 two-parameter tool, the description covers the core purpose, checks, and return values, which is adequate. However, the unexplained 'strictness' parameter and the absence of an output schema leave contextual gaps about how to interpret results and configure the tool. It is minimally complete but not comprehensive.
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 50%: 'email' is described in the schema, but 'strictness' has no description and is not explained in the tool description. The description does not clarify how strictness affects the risk score or verdict, leaving a semantic gap that the description fails to bridge.
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 uses a specific verb ('Check') and resource ('an email'), then enumerates six distinct validation dimensions (syntax, MX records, disposable providers, role accounts, homograph lookalikes, domain age). This makes the tool's purpose unmistakable and clearly differentiates it from sibling tools like score_domain or score_ip, which target other entities.
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 implies usage context (email risk assessment) but provides no explicit guidance on when to choose this tool over siblings, nor any exclusion criteria or prerequisites. It lacks 'use this when' language and does not mention alternatives, so usage context is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or action: phone, device, domain, IP, user (aggregate), agent, and email. The descriptions clearly separate individual signal scoring from the combined user scoring, and cryptographic verification is uniquely assigned to verify_agent. No two tools overlap in purpose.
Most tools follow the score_<object> pattern (score_device, score_domain, score_ip, score_user), but lookup_phone and verify_email/verify_agent deviate by using different verbs. The naming is still readable and logically grouped, though a more consistent prefix like score_phone and score_email would improve uniformity.
Seven tools cover the core signals for signup risk assessment without unnecessary redundancy. Each tool serves a clear purpose, and the count is well within the typical 3-15 range for a focused API.
The set covers the primary data points used in fraud/risk evaluation: phone, IP, email, domain, device, and a combined user score, plus a cryptographic agent verification for advanced scenarios. There are no obvious dead ends or missing lifecycle operations for this read-oriented risk assessment domain.