email_checkDeliverability probe for an email address without sending anything: syntax validation, live MX lookup (with A/AAAA fallback per RFC 5321), disposable-domain detection, and typo suggestions for common providers. Use it to validate an address before sending to it, storing it, or accepting a signup. LLMs cannot do the DNS part; this is a live check.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | The email address to check. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint and openWorldHint. The description adds that nothing is sent, describes the live MX lookup with RFC 5321 fallback, and notes the limitation that LLMs cannot perform the DNS part. This enriches the behavioral model beyond the annotations, though omitted details like rate limits or response shape would push it higher.
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?
Three sentences, each earning its place: the first defines scope, the second gives concrete use cases, the third explains why the tool is necessary. No filler and information is front-loaded.
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-parameter, read-only tool with no output schema, the description covers purpose, usage, and behavior well. The only gap is that it does not describe what the result looks like (e.g., boolean vs. report) or how to interpret typo suggestions, which an agent might need to know.
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 only parameter 'email' is fully described in the schema ('The email address to check'). With 100% schema coverage the baseline is 3; the description's mention of syntax validation and address checks adds some context but no new syntax or format details, so it does not elevate the score.
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 is a specific and actionable statement: 'Deliverability probe for an email address without sending anything' plus enumerates components (syntax validation, MX lookup with A/AAAA fallback, disposable-domain detection, typo suggestions). This clearly distinguishes it from siblings like dns_query (DNS-only) and inbox_* (message operations).
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?
Explicitly states when to use: 'validate an address before sending to it, storing it, or accepting a signup,' and warns 'LLMs cannot do the DNS part; this is a live check.' However, it does not explicitly name alternative tools or state when not to use, so it stops 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.
Add one secure layer between your agents and this server.
Each tool has a unique, clearly defined purpose (counters, cron, DNS, email, fixtures, webhooks, KV, locks, name checks, regex, timers, timezone, URL checks). There is no functional overlap; even closely related tools like timer_schedule and cron_next are clearly separated by descriptions.
The dominant naming pattern is <resource>_<action> (e.g., inbox_create, kv_get, lock_acquire, tz_convert). A few tools deviate, such as counter_next and cron_next (resource_qualifier), fixture_rows (resource_noun), and request_tool (verb_noun), but these are minor and do not obscure the overall pattern.
At 24 tools, the server exceeds the typical 3-15 range, leaning heavy. The tools cover many independent utility categories, each with a minimal set of operations, but the overall count feels slightly excessive for a single server, though it is justified by the broad scope.
The server provides complete lifecycles for its functional areas: KV (set/get/list/delete), inbox (create/poll/delete), locks (acquire/release), timers (schedule/status/cancel/verify). Each utility is self-contained, and the request_tool offers a path for extending the surface. No obvious gaps or dead ends within the intended domain.