DMARC/SPF/DKIM/MX checks, email score, 100-domain bulk score, webhook watch alerts (x402 USDC).
Scored across 8 tools
The three scoring tools overlap substantially: email_security_score, email_security_score_batch, and bulk_email_security_score differ mainly by batch size and price. check_domain_email_security also overlaps with scoring since it inspects the same DNS records for free. Descriptions help distinguish them, but tool selection still requires careful attention to batch size and payment model.
Naming is readable but mixed: some tools use verb_noun forms like check_email_address and check_domain_email_security, while others are noun-oriented like email_fix_plan, pricing, and watch_status. The single/batch scoring pair is somewhat consistent, but bulk_email_security_score uses a different prefix convention than email_security_score_batch.
Eight tools is a reasonable size for an email security assessment service, covering single checks, batch/bulk scoring, remediation planning, pricing, and watch status. The count is slightly inflated by three separate scoring variants that could potentially be consolidated.
Core assessment workflows are well covered: domain and email checks, scoring, bulk scoring, and fix plans. However, watch_status references a watch created via POST /v1/watch, but there is no tool to create, list, update, or cancel watches, leaving a notable lifecycle gap.
Score up to 100 domains' email security in one call (SPF 30, DMARC 40, DKIM 25, MX 5 from live DNS): per-domain score, grade and issues, plus a summary with grade counts, domains missing DMARC or SPF, and the worst 10. For MSPs and agents checking a client or vendor list. Costs $0.50 USDC via x402; errors are not charged.
| Name | Required | Description | Default |
|---|---|---|---|
| domains | Yes | Domains, 1-100 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds traits the annotations cannot express: live DNS lookups (openWorld), a $0.50 USDC x402 cost, and the important billing rule that errors are not charged. Annotations only cover the read-only/idempotent safety profile, so the payment and failure-cost behavior here is genuinely additive.
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: what it does and its scoring model first, return contents second, audience and cost last. No filler, and the most decision-relevant 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?
With no output schema, the description carries the return-value burden and does so explicitly: per-domain score, grade and issues, plus a summary with grade counts, domains missing DMARC/SPF, and the worst 10. Cost and error behavior are also covered, so nothing material 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?
Only one parameter, and schema description coverage is 100% ('Domains, 1-100'), so the schema already documents the input fully. The description restates the 1-100 cap but adds no syntax, format, or normalization guidance beyond it, matching the baseline 3 for high coverage.
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 with explicit scope: 'Score up to 100 domains' email security in one call, and names the exact scoring dimensions and weights. The 'bulk'/'up to 100 domains in one call' framing cleanly separates it from the single-domain siblings like check_domain_email_security and email_security_score.
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 clear usage context — 'For MSPs and agents checking a client or vendor list' — which tells the agent this is the batch path. It does not, however, explicitly name a single-domain alternative or state when not to use it, so it stops short of the 5 bar.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Look up a domain's MX, SPF (record, DNS lookup count, all qualifier), DMARC (policy, rua) and DKIM (common selectors, key size) from live DNS and list issues. No payment.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain, e.g. example.com (an email or URL on it also works) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds modest context — live DNS lookups and an issues listing — but says nothing about rate limits, latency, or failure behavior, so its added value is limited.
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 record enumeration is dense and front-loaded with 'Free', and most of the sentence earns its place. 'No payment.' at the end merely restates 'Free' and is wasted space.
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 correctly compensates by enumerating what is checked and reported (records plus an issues list). For a single-parameter read tool with full annotation coverage, nothing essential is missing, though the return shape remains only loosely characterized.
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% and the single 'domain' parameter is already fully documented, including that an email or URL will also work. The description adds no syntactic or format detail beyond the schema, so the baseline 3 for high coverage 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?
The description gives a specific verb (check/look up) and resource (a domain's email security) and enumerates the exact records retrieved (MX, SPF, DMARC, DKIM), so the agent knows precisely what it does. It does not explicitly differentiate itself from the domain-vs-address sibling 'check_email_address', leaving that distinction to inference from the name.
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?
There is no when-to-use or when-not-to-use guidance and no routing to alternatives such as check_email_address, email_fix_plan, or email_security_score. The repeated 'Free'/'No payment' hints at a pricing consideration but never states the condition under which this tool should be chosen.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check one email address: syntax, MX / null MX, disposable domain, role account, free provider; verdict ok / risky / undeliverable. No SMTP probe. Costs $0.01 USDC via x402; errors are not charged.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Email address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description goes further by disclosing cost ($0.01 USDC via x402), the billing rule that errors are not charged, and the negative behavior that no SMTP probe is performed. Those are material traits an agent cannot derive from annotations or schema.
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?
One dense sentence that front-loads the action and scope, followed by a short constraint and payment clause. No filler, no restatement of the tool name, and every clause carries distinct information.
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 one-parameter read tool with no output schema, the description covers what is checked, the verdict enum, the absence of SMTP probing, and the cost model. It stops short of describing what accompanies the verdict (e.g. which signals triggered a risky rating), which is the only remaining gap.
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?
There is a single parameter with 100% schema description coverage, so the schema already carries the parameter definition and the baseline is 3. The description adds no format, normalization, or edge-case guidance for the email argument beyond what the schema states.
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 (check) and resource (one email address) and enumerates exactly what is evaluated: syntax, MX / null MX, disposable domain, role account, free provider. It also names the output verdict space (ok / risky / undeliverable), so an agent knows precisely what this returns without opening anything else.
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?
"Check one email address" scopes it to single-address validation, which implicitly distinguishes it from the domain-level sibling check_domain_email_security. "No SMTP probe" clarifies a boundary of the check. However, it never explicitly names an alternative tool or states when-not to use this one, so routing is inferred rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Email security fix plan for one domain: the exact SPF, DKIM and DMARC records to publish (create / replace / keep, name, value, why), in order, with click-path steps for the domain's DNS host and a staged DMARC rollout. Non-sending domains get a lock-down set. Costs $1 USDC via x402; errors are not charged.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain, e.g. example.com (an email or URL on it also works) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower, and the description adds real value beyond them: a $1 USDC x402 charge and the fact that errored calls are not billed. It also discloses the shape of the plan (ordered records, click-path steps, staged DMARC rollout).
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?
Front-loaded with the core purpose, then packed with concrete deliverable detail; every clause (record actions, ordering, click-paths, rollout, lock-down set, pricing) carries information. Slightly dense, but nothing is wasted or repeated.
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 and no annotations explaining returns, the description carries that burden well, spelling out exactly what comes back (records with name/value/why and action, in order, plus host-specific steps and a staged rollout). Cost and error-billing behavior are also covered, leaving no material gap for invoking 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?
There is a single parameter and schema description coverage is 100%, so the schema already documents the domain format (including that an email or URL works). The description's 'for one domain' adds scope framing but no syntax or format detail beyond the schema, matching the baseline 3 for a fully documented single parameter.
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 names a specific verb+resource ('Email security fix plan for one domain') and enumerates the deliverable: SPF, DKIM and DMARC records with create/replace/keep actions, ordered, plus DNS-host click-paths and a staged rollout. This is clearly distinguishable in substance from the check/score siblings, though it never names an alternative to sharpen the contrast.
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?
Usage is implied rather than stated: an agent can infer this is the remediation step after check_domain_email_security or email_security_score, but the description never says when to reach for it versus those siblings. The only conditional guidance is the behavioral note that non-sending domains get a lock-down set, which is about output, not tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Grade a domain's email security 0-100 (A-F): SPF 30, DMARC 40, DKIM 25, MX 5, from live DNS, with findings and the top 3 fixes. Read-only. Costs $0.01 USDC via x402; errors are not charged.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain, e.g. example.com (an email or URL on it also works) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description still adds genuinely new context: the data source is live DNS, the call costs $0.01 USDC via x402, and failed calls are not charged. It does not say anything about latency or rate limits.
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?
Very dense but front-loaded: the grade, the weighting, the data source, the safety/cost terms all appear in order with no filler. Slightly run-on across semicolons, but no sentence is wasted.
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 one required param, full schema coverage, no output schema and rich annotations, the description still names the return contents (grade, findings, top 3 fixes) and the cost model. Only the A-F grade mapping from the 0-100 score is left unstated.
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% and the single 'domain' param already documents that an email or URL on the domain also works. The description adds no parameter-level detail beyond the schema, 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?
Specific verb+resource: 'Grade a domain's email security 0-100 (A-F)' with the exact scoring weights (SPF 30, DMARC 40, DKIM 25, MX 5) and output shape. It does not, however, explicitly differentiate itself from the sibling check_domain_email_security or email_fix_plan, whose scope overlaps with the 'top 3 fixes' promise.
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?
Usage is only implied by the grading/scoring framing and the stated $0.01 cost; there is no explicit when-to-use or when-not-to-use, and no routing to check_domain_email_security or email_fix_plan for the overlapping jobs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Score 2 to 5 domains' email security in one call (the same SPF/DMARC/DKIM/MX score, grade and findings as email_security_score), lowest score first. Costs $0.04 USDC via x402; if no domain can be scored it errors and is not charged.
| Name | Required | Description | Default |
|---|---|---|---|
| domains | Yes | 2 to 5 comma-separated domains |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing cost ($0.04 USDC via x402), the failure mode ('if no domain can be scored it errors and is not charged'), and result ordering (lowest score first). Those are exactly the non-obvious traits an agent needs before spending money on a call.
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?
A single tight sentence with the capability front-loaded and the cost/error caveat appended as a parenthetical. No filler or restated title.
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?
Covers the score/grade/findings return shape in lieu of an output schema, plus cost and error/charge behavior. For a one-parameter paid read tool, nothing an agent needs to call it safely 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 description coverage is 100% and the schema already says '2 to 5 comma-separated domains', which the description repeats rather than extends. No extra guidance on delimiter handling, duplicates, or partial-failure semantics per domain; 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 ('Score 2 to 5 domains' email security in one call') and explicitly equates the output to the sibling email_security_score (SPF/DMARC/DKIM/MX score, grade, findings). The '2 to 5' bound implicitly separates it from the single-domain and bulk siblings, so an agent can pick it without opening a 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?
The '2 to 5 domains in one call' framing plus the reference to 'the same ... score as email_security_score' tells the agent this is the batch form of that sibling. It does not explicitly state when to prefer bulk_email_security_score instead, so the multi-sibling routing is inferred rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Prices of the paid tools, payment network and receiving address.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description's one real addition is that the call itself is free (a cost trait not in annotations) and that the payload includes payment network and a receiving address. It does not describe response shape or whether payment details are conditional on a paid plan.
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?
Very short with no filler, and the cost note ('Free.') is front-loaded. The telegraphic, comma-spliced phrasing ('payment network and receiving address') makes the second sentence slightly harder to parse than a clean clause would, but nothing is wasted.
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 input params, no output schema and full annotation coverage, the remaining burden is telling the agent what comes back — and the description does list the three returned items (prices, payment network, receiving address). A little more on the shape of the pricing data (per-tool amounts, currency) would make it fully self-sufficient.
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?
Zero parameters and 100% schema description coverage, so per the rubric the baseline is 4. The description adds nothing param-related, but there is nothing to add.
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 names the resource it returns — prices of the paid tools, plus payment network and receiving address — which is specific enough to separate it from the sibling email-security tools. It lacks an explicit verb ('retrieve/return'), so it reads as a fragment rather than a full statement of purpose, but the resource is unambiguous.
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?
'Free.' hints that calling it costs nothing, which weakly implies 'safe to call anytime', but there is no statement of when to use this vs. siblings, no prerequisites, and no exclusions. The agent gets no routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free. Status of a paid email setup watch (created with POST /v1/watch): items, expiry, last check, last webhook delivery and current SPF/DMARC/DKIM/MX state. Needs the webhook_secret from creation.
| Name | Required | Description | Default |
|---|---|---|---|
| watch_id | Yes | Watch id, e.g. msw_abcdefghijklmnop | |
| webhook_secret | Yes | The webhook_secret returned once when the watch was created (required to read status) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds real value by disclosing that the call is free and that authentication requires the webhook_secret issued once at creation. It also lists the returned state fields, which matters since no output schema exists.
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, front-loaded with the cost note followed immediately by what the call returns and what it requires. 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 correctly compensates by enumerating the returned status fields, and it covers the auth prerequisite. Minor gaps remain, such as the shape of the 'items' collection and whether the state checks are live or cached.
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%, so both parameters are already documented, including the msw_ pattern and the webhook_secret provenance. The description's mention of the webhook_secret largely restates the schema and adds no format or constraint detail beyond it.
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 resource and operation: retrieves the status of an email setup watch, and enumerates exactly which fields come back (items, expiry, last check, last webhook delivery, SPF/DMARC/DKIM/MX state). It is clearly not one of the sibling email-security checkers, though it doesn't explicitly name any alternative to distinguish itself from.
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?
Usage is implied rather than spelled out: the agent learns the watch was created with POST /v1/watch and that the webhook_secret from creation is needed. There is no explicit when-to-use / when-not statement or reference to a sibling tool for comparison.
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.
email_security_score_batchwatch_status2 fields changedInput schema / properties / webhook_secretAdded value: +{
+ "description": "The webhook_secret returned once when the watch was created (required to read status)",
+ "maxLength": 200,
+ "minLength": 8,
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "watch_id"
-]New value: +[
+ "watch_id",
+ "webhook_secret"
+]bulk_email_security_scorewatch_statuscheck_domain_email_securitycheck_email_addressemail_fix_planemail_security_scorepricingDaily SPF, DKIM, DMARC and MX monitoring with webhook alerts, plus free sending-domain audits.
Pay-per-call domain and email security check: SPF, DKIM, DMARC, TLS, DNSSEC, BIMI, with exact fixes.
API uptime monitor, health check, downtime alerts, webhook alerts. x402 USDC.
API uptime monitor, health check, downtime alerts, webhook alerts. x402 USDC.
Add one secure layer between your agents and this server.