Email validation for AI assistants: verdict, risk score, evidence. Free: 100 checks a month.
Scored across 5 tools
Each tool targets a distinct action: single validation (validate_email), bulk submission (submit_bulk_job), async progress polling (get_job_status), per-row result fetching (get_job_results), and verdict explanation (explain_verdict). The status/results pair is the closest overlap but their descriptions clearly delineate progress metadata versus row-level data.
All five tools follow a uniform pingvalid_verb_noun pattern (explain_verdict, get_job_results, get_job_status, submit_bulk_job, validate_email). No mixing of conventions or vague verbs.
Five tools is well-scoped for an email-validation service, covering single, bulk, job polling, results, and explanation without redundancy. Each tool earns its place in the lifecycle.
The surface covers the full validation lifecycle from single check through async bulk submission, polling, and result retrieval, plus a helpful explanation utility. Minor gaps such as job cancellation or account/credit-balance introspection are not present but are workable around.
Render a natural-language explanation of a verdict you already received from pingvalid_validate_email. Pure transformation — no credits charged. Requires the validate:single scope.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| verdict | Yes | ||
| risk_score | Yes | ||
| tier_results | Yes | The tier_results map from a prior validate call. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive semantics. The description adds two pieces of behavioral context the annotations cannot convey: no credits are charged and the validate:single scope is required. It stops short of describing output format or failure modes.
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?
Two short sentences with zero filler; the transformation/cost fact is front-loaded and the precondition is stated second. Every clause earns its place.
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?
No output schema exists, yet the description conveys that the return is a natural-language explanation, which is the essential expectation for an agent. Provenance, cost, and auth scope are all covered, leaving only minor gaps around output size or formatting.
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 description coverage is only 25%, but the schema itself carries enums, bounds, and a description for the nested tier_results object. The description adds provenance meaning — all four inputs come from a prior validate call — but does not explain any individual parameter, so it only partially compensates for the coverage gap.
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?
States a specific verb and resource ('render a natural-language explanation of a verdict') and explicitly ties the input to the output of the sibling tool pingvalid_validate_email. An agent can distinguish this from validate_email without opening the schema.
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?
Clearly establishes the usage precondition: you must already have a verdict from pingvalid_validate_email, and this call is a pure transformation that costs no credits. It does not name when NOT to use it or an explicit alternative, 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.
Fetch a bulk job's per-row results as JSON pages (25/page): email, verdict, risk score, cost. Filter by verdict (e.g. verdict=valid for the clean list). Free to call. Requires the read:results scope.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| job_id | Yes | Job id returned by pingvalid_submit_bulk_job. | |
| verdict | No | Only rows with this verdict. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description doesn't need to restate safety. It adds genuinely useful context beyond them: 25-row pagination, that the call is free, and the read:results auth requirement.
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 tight sentences that front-load what is returned, then filtering, then cost/auth. No filler or 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?
With no output schema, the description carries the return-value burden and discharges it by naming the per-row fields and pagination. Auth scope and cost are also covered, so an agent has everything needed to call it correctly.
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 67% (job_id and verdict documented, page not), so some compensation is expected. The description adds the page size (25/page) that the schema omits, and clarifies verdict filtering with a valid-list example, adding meaning beyond the raw enum.
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?
States a specific verb (Fetch) and resource (a bulk job's per-row results), and enumerates the returned fields (email, verdict, risk score, cost). It implicitly separates itself from pingvalid_get_job_status by focusing on per-row results, but never names a sibling explicitly, so it stops short of top-tier differentiation.
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?
Gives one concrete filter example (verdict=valid for the clean list) and states the required read:results scope, which hints at usage context. However, it never says when to prefer this tool over pingvalid_get_job_status or pingvalid_explain_verdict, leaving the alternative selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Poll a bulk validation job: progress percent, per-verdict counts, accumulated cost, and a results_url (NDJSON) once completed. Free to call. Requires the read:results scope.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | Job id returned by pingvalid_submit_bulk_job. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world. Beyond those, the description adds genuinely new context: no cost impact ("Free to call"), the required read:results scope, and the state-dependent return (results_url only once completed). Missing only rate-limit or polling-interval guidance to reach 5.
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?
Two tight sentences, zero filler. The return payload is front-loaded before the operational constraints, so an agent skimming gets the primary value immediately.
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?
With no output schema, the description carries the burden of describing the return value and does so precisely, enumerating the fields and the conditions under which results_url appears. Auth scope and cost are also covered, leaving nothing essential unstated for a one-parameter status tool.
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 single job_id parameter is fully documented in the schema (100% coverage), including its link back to pingvalid_submit_bulk_job. The description adds no format, bounds, or lineage detail beyond what the schema already provides, so the baseline 3 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?
States a specific verb (poll), resource (bulk validation job), and enumerates exactly what comes back: progress percent, per-verdict counts, accumulated cost, results_url. The mention of results_url as the NDJSON pointer implicitly distinguishes it from pingvalid_get_job_results, which fetches the payload itself.
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?
"Poll" implies the usage pattern (call repeatedly until complete, then fetch results), and "Free to call" hints that frequent polling is acceptable. However, it never explicitly states when to prefer this over pingvalid_get_job_results, nor does it say anything about when not to call it or recommended polling cadence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit up to 1000 email addresses for asynchronous validation. Returns immediately with a job_id; poll pingvalid_get_job_status until it completes. Requires the validate:bulk scope.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Pricing depth: quick (T1–T5) | standard (T1–T6, default) | deep (T1–T7, needs a paid plan or a top-up). | standard |
| emails | Yes | Up to 1000 email addresses to validate in one batch. | |
| legitimate_interest | Yes | Must be true. Asserts the submitter has a legitimate interest in validating these addresses (required by the Terms of Service). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds real context beyond the annotations: asynchronous execution, immediate return with a job_id, and a required validate:bulk scope (auth requirement). Annotations already cover the read-only/idempotency/destructive profile, so the remaining gap is minor.
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 short sentences, front-loaded with the action and capacity, then the async follow-up, then the prerequisite. No filler.
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?
No output schema exists, yet the description still explains the return value (job_id) and the polling workflow, and it discloses the required scope. An agent has everything needed to invoke and follow up correctly.
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 description coverage is 100%, including the tier enum's pricing-depth semantics and the legitimate_interest constraint, so the schema carries the parameter burden. The description only restates the 1000-address cap and adds no new parameter meaning; baseline 3 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?
States a specific verb and resource ('Submit ... email addresses for asynchronous validation') plus a concrete capacity bound ('up to 1000'). This clearly separates it from the single-address sibling pingvalid_validate_email and from the polling siblings.
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 tells the agent what happens next: 'Returns immediately with a job_id; poll pingvalid_get_job_status until it completes,' naming the follow-up sibling. It does not explicitly contrast bulk vs. single validation, but the async/batch framing makes the choice inferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate a single email address. Returns a deliverability verdict (valid/risky/invalid/unknown) with tier-by-tier evidence and a 0–100 risk score. Spends 1 credit (2 on deep); cache hits are free on quick/standard.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Pricing depth: quick (T1–T5) | standard (T1–T6, default) | deep (T1–T7, needs a paid plan or a top-up). | standard |
| Yes | Email address to validate. Internationalized (SMTPUTF8) supported. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover safety (readOnlyHint=false, openWorldHint=true, idempotent=false), and the description adds genuinely new behavior: credit cost (1 credit, 2 on deep) and free cache hits on quick/standard. This explains why the call is not free/read-only, which the annotations alone do not 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?
Two sentences, zero filler, and the most decision-relevant facts (what it validates, what it returns, what it costs) are front-loaded. The parenthetical pricing detail is compressed and earns its place.
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?
No output schema exists, so the description takes on the return-value burden and does so well by enumerating the verdict values and the 0–100 score. It stops short of describing the shape of the 'tier-by-tier evidence', but for a two-parameter tool this is close to complete.
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 tier enum is fully documented with T1–T7 depth per level, so the schema carries the parameter burden. The description reinforces the deep-tier cost but adds no syntax or default beyond what the schema already states, making 3 the correct baseline.
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?
States a specific verb+resource ('Validate a single email address') and immediately scopes it to one address, which distinguishes it from the bulk-oriented sibling pingvalid_submit_bulk_job. It also names the output artifact (deliverability verdict plus risk score), so an agent knows exactly what this produces.
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 word 'single' implies this replaces bulk submission for one-off checks, and the credit-cost note helps an agent reason about depth, but no sibling is named and there is no explicit when-to-use vs pingvalid_explain_verdict or the job-status tools. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
pingvalid_get_job_resultspingvalid_submit_bulk_job2 fields changedInput schema / properties / tier / descriptionAdded value: +"Pricing depth: quick (T1–T5) | standard (T1–T6, default) | deep (T1–T7, needs a paid plan or a top-up)."Input schema / properties / webhook_urlRemoved value: -{
- "description": "Optional HTTPS URL — receives an HMAC-signed completion event.",
- "format": "uri",
- "type": "string"
-}pingvalid_validate_email1 field changedInput schema / properties / tier / descriptionPrevious value: -"Pricing depth: quick (T1–T5) | standard (T1–T6, default) | deep (T1–T7)."New value: +"Pricing depth: quick (T1–T5) | standard (T1–T6, default) | deep (T1–T7, needs a paid plan or a top-up)."pingvalid_explain_verdictpingvalid_get_job_statuspingvalid_submit_bulk_jobpingvalid_validate_emailEmail verification and domain intelligence for AI agents. MX, RDAP, SSL checks. 25 free credits.
Validate emails (MX, disposable, role, typo) and phone numbers, singly or in batches, for AI agents.
Email verification for AI agents: syntax, MX, disposable, role, score. $0.001 USDC/call via x402.
Email verification for AI agents — verify, clean & validate emails; self-onboard + crypto pay
Add one secure layer between your agents and this server.