Programmatic email deliverability testing for AI agents. Create inbox placement tests across Gmail, Outlook, Yahoo, Mail.ru, Yandex — get per-provider placement (Inbox/Spam/Promotions), SPF/DKIM/DMARC auth, Rspamd & SpamAssassin verdicts, DNS health, and live SSE results.
Scored across 3 tools
Each tool targets a distinct part of the workflow: listing providers, creating a test, and reading a test by token. There is no overlap between guest_providers_list, guest_tests_create, and guest_tests_get, so an agent can easily select the right one.
All tools follow a consistent `guest_<resource>_<verb>` pattern, making them predictable and readable together. The only minor deviation is that verbs appear at the end rather than the common verb-first convention, but the set itself is internally uniform.
Three tools form a tightly scoped, minimal surface for a free inbox-placement test service: list providers, create test, get results. Each tool earns its place and there is no unnecessary bloat.
The create-and-read lifecycle is covered, but there is no way to list existing tests or delete them, and the description explicitly notes missing reporting modes. These gaps are manageable but represent notable missing operations for the domain.
List currently available free test providers; no account or API key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full load and does contribute one genuinely useful fact: no authentication is required. It also implies read-only via 'list'. It does not disclose rate limits, quota behavior, or what a returned provider entry contains, which matters for a tool agents will call before creating tests.
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 compact clause with no filler, and the availability qualifier ('currently available') and auth note are both front-loaded. It is efficient, though slightly terse to the point of ambiguity about what a 'provider' is.
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 zero-param read tool this covers what it does and the auth precondition, but with no annotations and no output schema the description is the only source of return-shape information and says nothing about what a provider object looks like or whether results are filtered/limited. Adequate to call, thin for interpreting the result.
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, so per the baseline this is a 4. The description correctly gives no parameter detail and instead spends its words on availability and auth, which is the right allocation.
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 (list) and resource (free test providers), and the 'guest' prefix plus the sibling names (guest_tests_create, guest_tests_get) make clear this is the discovery step rather than a test-execution step. 'Providers' is slightly underspecified, but the intent is legible 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?
The phrase 'no account or API key' implies this is the zero-auth entry point and is likely the right first call before guest_tests_create, but the description never says so explicitly or names an alternative. Usage is implied rather than directed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create one free inbox-placement test. Requires sender email, not email-login. Returns token and seed addresses; send the real message before polling for measured results. Notification emails default off. Never automatically replay this POST.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| providers | No | ||
| emailLocale | No | ||
| senderLinkReports | No | ||
| finalReportEnabled | No | ||
| placementChangeAlertsEnabled | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden and does well: it discloses the return payload (token and seed addresses), that notification emails default to off, that the operation is non-idempotent and must not be auto-replayed, and an input precondition that isn't obvious from the 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?
Telegraphic but front-loaded and waste-free: purpose first, then prerequisites, return shape, workflow, defaults, and the safety caveat. Every sentence adds a distinct fact.
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 workflow and partially the return shape with no output schema to lean on, but for a 6-parameter tool with zero schema descriptions, the optional parameters (providers, locale, report flags) have no meaning anywhere. The description does not explain what is polled or what the token is used for.
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 0% across 6 parameters, so the description must compensate. It clarifies the required email semantically (sender address, not the login email) and hints that notification-type flags default off, but providers, emailLocale (the only enum), senderLinkReports, and finalReportEnabled are never explained.
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 ("Create one free inbox-placement test") plus a scope constraint (single, free test). The create action naturally separates it from the get and list siblings without needing to name them.
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 a real workflow: create, send the actual message to the seed addresses, then poll for measured results, and warns against automatic replay of the POST. It also excludes a plausible wrong input ("not email-login"). It stops short of naming guest_tests_get as the polling tool or stating when to prefer alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a guest test by its saved private report token, including measured results and ai_context. Pending is not delivery. No test listing, deletion or managed-key reports.
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses returned content (measured results and ai_context) and hints at pending-state semantics, but the phrase 'Pending is not delivery' is too cryptic to fully clarify status behavior, and auth/error behavior is not described.
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 short and front-loads the core operation. The middle sentence ('Pending is not delivery') is vague enough to feel like jargon rather than clear guidance, but the overall structure remains efficient.
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 simple read tool with one parameter and no output schema, the description gives the essential lookup context and names returned fields. It is missing clearer explanation of pending semantics, error handling, and the privacy/authorization assumptions around the report token.
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 0%, so the description must compensate for the single token parameter. It does add meaning by identifying the token as a 'saved private report token', but it does not explain token provenance, expected format, or failure cases beyond what the schema pattern already enforces.
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 states a specific verb (Read) and resource (guest test), and anchors it to the saved private report token. It also explicitly rules out listing, deletion, and managed-key reports, which separates it from the create and provider-list 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?
It clearly implies use when you have a saved private report token and need measured results plus ai_context. The exclusion sentence gives useful boundaries, though it does not explicitly name guest_tests_create as the alternative for creating tests.
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.
guest_providers_listguest_tests_createguest_tests_get
Add one secure layer between your agents and this server.