Nymwell Lookup

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

Annotations already declare readOnly/openWorld/non-destructive, so safety is covered; the description adds real value by bounding scope ('Public records only; owner contact details are not returned') and by listing the data surfaces an agent can expect. It does not say what happens for unregistered or unparsable domains, which is the remaining behavioral 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?

A single front-loaded sentence that opens with the usage trigger and then enumerates the returned record types; each clause conveys distinct information about output, and the scope caveat closes it cleanly with no filler.

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 by enumerating record categories plus the exclusion of owner contact data. Only the failure/not-found behavior is left unspecified, which is minor for a read-only lookup.

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% and the single 'domain' parameter has no type/format detail in the schema beyond 'string'. The description compensates partially by implying one existing, registered domain (not a list, not a TLD), but it never shows the expected form (e.g. bare 'example.com', no scheme or path).

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 (look up one existing domain's public records) and enumerates exactly what is returned: registrar, registration/expiry dates, lock status, nameservers, DNS host, MX/SPF/DMARC, HTTPS reachability. The phrase 'one existing domain' implicitly separates it from list-oriented siblings like search_domains and suggest_domains, but no sibling is named explicitly.

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?

'Use this when someone asks about one existing domain' gives a clear triggering condition and the singular scope rules out the search/suggest siblings. It does not spell out when-not-to-use or explicitly name get_tld_info/screen_domains as alternatives, which keeps it one notch below the top.

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 readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by enumerating the data returned: registration/renewal/transfer prices, allowed terms, grace period after expiry, WHOIS privacy, DNSSEC and HSTS preload. It does not cover freshness/currency of pricing data, but for a read-only lookup this is a solid disclosure.

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 that starts with the usage trigger and then enumerates the returned data. Tight and readable; the long enumeration of fields is justified because it conveys scope that is not in any structured field.

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 return-content enumeration is needed and present. However, the single input parameter remains completely undocumented, and nothing is said about how many results to expect or whether multiple TLDs are batched. Adequate but leaves a real input gap.

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 sole parameter (a 'tlds' array, max 10) is not mentioned in the description. The examples (.com, .ai, .io) hint at what values look like, but they do not state that input is a list, that up to ten are allowed, or that it is optional. The description fails to compensate for the schema gap.

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 ('what a domain ending costs or what its rules are') with concrete examples (.com, .ai, .io), so an agent can tell this is TLD-level lookup rather than per-domain lookup. It does not name or differentiate from the sibling domain_info, which is the most likely confusion point.

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?

'Use this when someone asks...' gives a clear triggering context for the tool. There are no explicit when-not conditions or named alternatives (e.g., domain_info for a specific registered domain), but the usage context is unambiguous.

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 (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the description's added value is the provenance-and-accuracy caveat: results come from DNS and public registry records and are advisory rather than authoritative. It also discloses the 500-item ceiling and the tlds=["all"] sentinel. It stops short of saying anything about latency or rate limits when screening 500 names, which is the main remaining unknown for a bulk call.

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 primary use case, then the caveat that governs trust in the results. No filler and no 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?

With no output schema, the description carries the return-value burden and does so adequately by naming registration status, registrar, and expiry date. The one substantive gap is that it never clarifies which of the two input shapes to use (bulk domains list versus one name across tlds), which matters for a 4-parameter tool with no required fields.

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 75%, so the schema already documents name, tlds, and details. The description adds real meaning for the tlds=["all"] sentinel and the 500 cap, and implies details via 'with its registrar and expiry date'. However, the `domains` parameter has no schema description and the description never explains the name+tlds versus domains calling modes, leaving the most ambiguous input undocumented in both places.

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 — bulk availability screening of domain names — plus the data sources (DNS and public registry records) and what is returned (registration status, registrar, expiry). It also explicitly contrasts itself with search_domains, so an agent can separate it from the four siblings without inspecting any 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?

Gives a clear use case (many names at once, up to 500, or one name across all endings), and an explicit when-not: this is a quick screen, not the registrar's answer, so names intended for a suggestion should be confirmed with search_domains. The alternative and the condition that selects it are both named.

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 safety (readOnly, non-destructive, open-world), and the description adds real substance beyond them: the lookup hits the live registrar, is capped at 20 names, and returns per-name registrability, first-year and renewal price in USD, plus a failure reason. It does not mention latency, rate limits, or partial-failure behavior.

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, zero filler, with the trigger condition front-loaded before the behavioral and routing details. Every sentence carries distinct 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?

No output schema exists, and the description compensates by spelling out the per-item return fields and the failure-reason case. The remaining gap is the unstated exclusivity between the single-domain and list-domain parameters, which an agent must guess at.

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 75%, giving a baseline of 3. The description does add the important combinatorial semantics that 'name' plus 'tlds' generates the candidate list versus passing exact domains, but it never clarifies whether 'domain' and 'domains' are mutually exclusive or how precedence works — the key ambiguity in this four-parameter, zero-required 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 and resource — checking domain name availability and price against a live registrar — with scope (up to 20 names, exact domains or name+endings). It also names the sibling screen_domains it is not, so an agent can separate the two without opening schemas.

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?

Explicit trigger ('when someone wants to know whether specific domain names can be registered and what they cost') plus a routing rule to use screen_domains first for many names. It does not contrast with suggest_domains or domain_info, so the alternative-space is only partly covered.

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 readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds genuine value by promising only domains "that can be registered now" and noting prices are returned, but it says nothing about result count, ranking, or whether availability is real-time or cached.

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 the trigger condition first and the outcome second. No filler, though the pricing/registrability clause slightly crowds the main purpose statement.

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?

No output schema, so the description must carry the return-value burden, and it partially does (names plus prices). However, with two parameters at 0% schema coverage and no sibling differentiation, the definition leaves key invocation decisions to inference.

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% for both parameters. The description only implies the keyword input; the 'tlds' filter (an array capped at 20 entries) is never mentioned, so an agent has no guidance on what to pass or what happens when it is omitted.

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 ("returns domain names that fit it") and adds a qualifier about registrability and pricing. It does not distinguish itself from close siblings like search_domains or screen_domains, which an agent could reasonably confuse it with.

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 clear triggering scenario: "when someone has a keyword or an idea but no name yet." That frames the use case well, but there are no exclusions or pointers to the alternatives (search_domains, screen_domains, domain_info) that cover adjacent needs.

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