Email Deliverability Checker

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

Annotations already cover safety (readOnly, idempotent, non-destructive) and open-world behavior, and the description adds genuinely useful detail: the 10-DNS-lookup limit on SPF, that problems are returned ranked by severity with a fix each, and that used email services are detected. It doesn't mention response time or failure modes for unreachable domains, keeping it below 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 sentences, zero waste. The full check surface is front-loaded and the return shape follows immediately, so an agent can grasp both purpose and output at a glance.

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: ranked problems, per-issue fixes, and detected email services. For a two-parameter read-only tool with full annotation coverage, nothing an agent needs to call it correctly 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 coverage is 100%, so both parameters are already documented, including the URL/email-address tolerance for 'domain'. The phrase 'DKIM keys on common selectors' hints at the dkim_selectors parameter but adds no format guidance beyond the schema's own example.

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 concrete resources (SPF, DMARC, DKIM, MX) for a domain. The email-DNS scope is unmistakable and clearly different from check_email_headers and check_sending_ip, which operate on messages and IPs respectively.

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 context is implied by the enumerated checks, but the description never says when to reach for this tool instead of check_email_headers or check_sending_ip, nor any prerequisites. The agent must infer routing from the subject matter.

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 declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds useful behavior beyond that: the checks are against Gmail/Yahoo bulk-sender rules, and any body included with the headers is ignored. It does not mention whether any live DNS/network lookups occur despite openWorldHint, a minor gap.

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, front-loaded with the action and an enumerated checklist, followed by the one operational note that matters. No filler or restatement of the 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?

For a single-input, read-only checker with no output schema, the definition covers what is validated and how to supply input correctly. It stops short of indicating the result shape (per-check pass/fail versus a summary), which an agent might want but can discover at call time.

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 single parameter is well documented. The description adds real value beyond the schema by specifying the expected form of the input — raw headers as the recipient received them, with a concrete Gmail path to obtain them — which reduces malformed input.

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 (a received email's headers) and enumerates exactly what is validated: SPF, DKIM/DMARC, alignment, one-click unsubscribe, TLS, rDNS, Message-ID. The focus on a received message's raw headers clearly separates it from check_domain and check_sending_ip, which operate on a domain or IP.

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 concrete acquisition instruction — use the full headers as the recipient got them, with the Gmail 'Show original' pointer — which is the key prerequisite for correct invocation. It does not explicitly say when to prefer check_domain or check_sending_ip, so alternatives are left implicit.

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 declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: a refused Spamhaus query is reported as unknown rather than as a listing, which tells the agent how to interpret an ambiguous result. It stops short of describing the overall response shape.

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, with the check list front-loaded and the interpretive caveat placed after it. Every clause conveys new 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?

With no output schema, the description still communicates the result categories an agent will receive: PTR value, whether it resolves back, per-blocklist listing status, and an 'unknown' state. What's missing is any sense of response structure or how multiple listings are aggregated.

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 parameter already documents 'IPv4 or IPv6 address of the sending server.' The description adds no format, hostname-handling, or edge-case guidance beyond that, so the baseline 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 a mail server's IP') and then enumerates exactly what is inspected: PTR, forward confirmation, and named DNSBLs. The IP-centric scope naturally separates it from check_domain and check_email_headers without the agent needing to open 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 framing implies the pre-send use case (validating a sending server's reputation), but the description never states when to reach for this versus check_domain or check_email_headers, nor any prerequisites such as needing the IP rather than a hostname. Usage is inferable, not stated.

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