InboxGuards Email Check

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only/idempotent/open-world safety profile, and the description goes well beyond them: no SMTP probe, no mail sent, no storage or logging, exactly one live DNS lookup via Cloudflare DoH, verdict vocabulary, and per-call cost with payment placement in _meta and the no-charge-on-error rule.

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 action and checks, then limitations, then cost and error semantics. It is dense but every clause carries distinct, decision-relevant information with no filler or repetition.

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?

There is no output schema, yet the description supplies the return vocabulary (ok/risky/undeliverable with plain reasons), the data-retention and privacy stance, billing mechanics, and failure behavior — everything an agent needs to invoke and interpret 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?

One parameter with 100% schema description coverage, so the schema already documents name, type and example. The description adds no format, normalization, or length constraints beyond what is already in 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 and resource ('check one email address') with an explicit enumeration of what is checked (syntax, MX/null MX/implicit A, disposable, role-account, free-provider). It clearly differentiates itself from the sibling validate_email by declaring it does far more than syntax validation.

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 routes the agent: 'Use validate_email first if you only need syntax,' and states the exclusion condition ('no SMTP probe is made... cannot confirm the mailbox exists'). It also covers the error/charging condition, which is a routing-relevant constraint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: $1 USDC per call via x402 with the payment key location, the fact that invalid input / unknown domain / DNS failure is not charged, that nothing is stored, and the 10-lookup SPF merge limit with DMARC staging behavior. This is exactly the extra behavioral detail the annotations cannot carry.

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 dense paragraph, but the purpose and deliverables are front-loaded and most clauses carry real information (providers detected, SPF merge, DMARC staging, pricing). It is on the long side, and the provider enumeration and payment mechanics could be tightened without loss.

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: it specifies the ordered record set, the per-host click paths, and error/charging semantics. An agent has everything needed to call it and interpret 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?

Schema description coverage is 100% and there is only one parameter, so the schema already documents that an email address or URL on the domain also works. The description adds no syntax or format detail beyond that, so the baseline 3 is appropriate.

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 ('get an email security fix plan for one domain') and enumerates the concrete deliverables: SPF/DKIM/DMARC records with action, name, value and rationale, plus DNS-host click paths. This is clearly distinguishable from the sibling validators (check_email_address, validate_email), which inspect addresses rather than produce a remediation plan.

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 explicit triggering contexts: 'when mail lands in spam, before a DMARC rollout, or for a client.' It also carves out a scope condition ('domains that send no mail get a lock-down set'). It does not name a sibling alternative or state when-not to use it, 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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, non-destructive, idempotent, closed-world), so the bar is lower; the description still adds real context beyond them by declaring the operation is free, incurs no payment, and makes no network request. It stops short of describing the shape of the returned price values.

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 'Free.' and then a single dense sentence covering return contents and constraints; nothing is wasted. The stacked parentheticals ('and of the HTTP-only email test report') add minor parsing friction.

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 parameters and no output schema, the description is responsible for signalling what comes back, and it does list the three returned items. It leaves open the exact format/units of the price, but for a zero-argument pricing endpoint this is largely 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?

The schema has zero parameters at 100% coverage, so the baseline is 4. The description reinforces this with 'No input', which is consistent and adds mild confirmation value but nothing beyond the empty schema.

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 (Return) and precisely enumerates the resource: the price of check_email_address, the payment network (Base), and the receiving address. It is immediately distinguishable from the sibling validation tools, which do work rather than quote cost.

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 by naming check_email_address as the priced item, so an agent can infer this is a pre-flight cost check, but it never states when to call it versus proceeding straight to the paid tool. No alternatives or exclusions are given, leaving usage to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly, idempotent, non-destructive, and closed-world. The description adds meaningful context beyond that: 'offline', 'No DNS lookup, no network request', clarifying that it will not verify deliverability or reachability, which is exactly the boundary an agent needs to know. Only the exact return shape (field names) is left unstated.

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 compact sentences, front-loaded with the key differentiator ('Free.') and the core action, with the no-network/no-payment caveats following. Zero waste.

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?

There is no output schema, so the description correctly compensates by naming what is returned ('normalized address and domain'). Combined with the offline/no-payment guarantees and the sibling routing hint, an agent has everything needed to call and interpret it.

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% with a single, self-explanatory 'email' parameter including a format example, so the schema does the heavy lifting. The description adds no syntax constraints or formatting guidance 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?

States a specific verb and resource ('check the syntax of an email address') plus the return value ('normalized address and domain'), all in one clause. It distinguishes itself from the sibling check_email_address by positioning itself as the pre-step.

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 names the sibling tool ('before paying for check_email_address') and the condition that selects this one instead (syntax-only, free). An agent has no ambiguity about when to call this versus the paid alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.