Zovo DNS Checker

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real substance on top: live public DNS via DoH, the specific outputs produced (MX hosts, SPF lookup count vs. the limit of 10, DMARC policy/reporting/alignment, DKIM keys, pass/warn/fail findings with fix and CSV report). External-dependency and scope facts are disclosed rather than left to inference.

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 sentences, front-loaded with the trigger conditions and with zero filler. The first sentence is a long synonym enumeration, which is dense but earns its place for routing; slightly heavy on commas.

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?

Though an output schema exists, the description still usefully summarizes the returned findings, and it covers the external-DNS dependency, the SPF limit, and the exclusions. Nothing an agent needs to invoke 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 description coverage is 100%, so both parameters are already documented in the schema, establishing a baseline of 3. The description adds only marginal meaning, noting that DKIM results depend on 'the selectors you give' but offering no extra syntax, defaults, or failure guidance beyond the 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+resource ('email DNS check') and enumerates the concrete artifacts it covers (DMARC, SPF, DKIM, MX) plus the mechanism (DNS-over-HTTPS). An agent can immediately tell this apart from the sibling lookup_dns_records.

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?

Opens with an explicit trigger list ('Use this when the user wants...') mapped to user vocabulary, then gives hard exclusions ('Do not use for internal DNS server visibility, full deliverability tests, or reading or sending mail'). Both the when and the when-not are stated.

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?

The annotations already cover read-only, idempotent, non-destructive and open-world behavior, and the description adds genuinely new context: the data source is live public DNS over HTTPS, TTLs are included, and a CSV report is produced. It stops short of describing rate limits, caching, or failure behavior for unresolvable domains, which an agent would still want.

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 sentences, front-loaded with the trigger conditions, then the behavior, then the exclusions. The record-type enumeration appears in both the behavior and exclusion sentences, but the repetition serves the boundary-setting purpose rather than wasting 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 an output schema present, the description needn't explain return values, and the rich annotations cover the safety profile. Between the description and schema, an agent has everything needed to decide when to call it and with what arguments.

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 both parameters are well documented in the schema, including the default-all behavior when 'types' is omitted. The description adds little beyond reinforcing the supported type list, 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?

The description gives a specific verb and resource ('Reads live public DNS records through DNS-over-HTTPS') and enumerates the exact record types returned, so the agent knows precisely what the tool produces. It does not name or contrast with the sibling check_email_dns, even though 'mx record check' overlaps that tool's territory, which keeps it below a 5.

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 states triggering user intents up front ('dns lookup, an mx record check, or a txt record lookup') and then gives explicit exclusions: internal DNS server visibility, reverse DNS of an IP, and record types outside the supported list. That is a clear when/when-not pair with nothing left to inference.

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