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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered; the description adds genuinely new behavioral context by enumerating the verdict values, the risk signals evaluated, and the advice field. It stops short of stating rate limits, latency, or behavior on malformed input.

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 purpose and followed by the return contract; the parenthetical lists are dense but each item is informative. Slightly list-heavy, but no filler sentences.

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, describing the verdict, risk score, reasons and advice field is exactly the missing information, and the accepted input form is covered too. Only minor gaps remain, such as error handling and whether results are 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 0% and the single property has no title-level detail, so the description carries the burden — and it does, explicitly stating it accepts either a bare domain or a full URL. That is the key ambiguity an agent would otherwise face, though input normalization rules (e.g. schemes, ports, trailing paths) remain unstated.

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 opens with a specific verb and resource ('Check whether a domain or URL is safe to open') and names the underlying resolver, which distinguishes it from the plain 'resolve' sibling. It is clear what the tool produces, though it never explicitly contrasts itself with 'resolve' or 'service_status'.

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: 'safe to open' suggests a pre-visit safety screen rather than raw resolution, which hints at the boundary with 'resolve'. There is no explicit when-to-use/when-not statement and no named alternative, leaving the agent to infer routing between siblings.

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 the safety profile is covered. The description adds real value by disclosing the return payload (records, rcode, DNSSEC validation status, blocking status, RFC 8914 Extended DNS Errors), which is important because no output schema exists. It does not cover failure modes such as NXDOMAIN handling or rate limits, keeping it below a 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, front-loaded with the operation and its trust properties before the parameter enumeration and return shape. The record-type list is long but earns its place given zero enum coverage in the schema.

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, no parameter descriptions and no enums, the description supplies the two things the structured data omits: the valid record types and the shape of the result including DNSSEC and blocking signals. What remains missing is guidance on distinguishing this from check_domain and what happens on resolution failure.

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% and the schema has no enum, so the description carries the full burden and does it: it enumerates all 15 legal record_type values, which the schema does not. The name parameter is left uncharacterized beyond the tool name implying a DNS name, and the A default is only in 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 (resolve) and resource (DNS name) and scopes it to ShieldDNS with DoH, DNSSEC and threat-blocking, which is far more than the title restated. It does not explicitly contrast with the sibling check_domain, so an agent must infer which one it wants when the task is 'look up a domain'.

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: the tool resolves a name and takes a record type, so an agent can guess it is the query primitive. There is no statement of when to prefer it over check_domain or service_status, and no mention of preconditions such as a required record_type default.

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, open-world behavior, so the safety profile is covered. The description adds genuinely useful context — two nodes with mutual 5-minute checks — which tells the agent data may be up to five minutes stale. It does not describe what the status response contains, so with annotations doing much of the work a 3 is fair.

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 front-loaded sentence with no filler; the parenthetical about the 5-minute mutual check carries real information rather than padding.

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-only tool the description is nearly sufficient, but with no output schema it never indicates what the status result looks like (per-node state, fields, overall health). That is the one piece an agent still has to discover by calling.

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?

With zero parameters there is no parameter semantics to explain, so the baseline of 4 applies. The description correctly adds no parameter chatter.

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 clearly identifies the resource ('Public status of the two ShieldDNS nodes') and its scope, distinguishing it from siblings like check_domain and resolve which perform lookups rather than health reporting. The verb is implicit in 'Public status of', but the intent 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?

There is no explicit statement of when to call this tool versus alternatives, nor any prerequisites. Usage is only implied by the word 'status'; an agent must infer that this is the health-check endpoint rather than being told.

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