OrbitFour

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

Annotations already declare read-only, idempotent, open-world, non-destructive, and the description reinforces with 'read-only' and 'Up to 10 names per call.' It adds genuine behavioral context beyond annotations: that a malformed name or unsold extension returns an error field rather than failing, and that a null 'available' means the registry could not be asked rather than the name being taken.

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?

The purpose is well front-loaded, but the bulk of the description is a field-by-field explanation of return values (first_term, pricing_source, purchasable, purchase_blocker, pricing_sources) for a tool that has an output schema. That material is largely redundant against structured data and dilutes the routing guidance the agent actually needs.

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?

Given a two-parameter, read-only lookup with a full output schema, the description covers the essentials: scope, batch limit, the exact-vs-search distinction, and error behavior for malformed names. The only omission is any mention of the transfer and TLD-requirements siblings.

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 the schema already documents both parameters including the max-10 limit. The description only restates the 10-name cap and adds no syntax or format detail for 'years' beyond what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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 — 'Look up exact domain names: whether each can be registered now, and its per-year registration, renewal and transfer price' — and explicitly contrasts with the sibling search_domains ('confirm a search_domains suggestion'). An agent can route between the two without opening either 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 clear usage context: 'Use it for names you already have and to confirm a search_domains suggestion,' naming the alternative and the condition that selects it. It does not address the other siblings (check_transfer, get_tld_requirements) or state when-not, so it falls 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?

Goes well beyond the readOnly/idempotent annotations by explaining failure semantics: transferable can be null when the registry was unreachable, and that null is explicitly not the same as locked. It also clarifies price meaning ('what the transfer would cost if it goes ahead') and the constraint that no auth code belongs here.

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?

The core action and price scope are front-loaded in the first sentence, and the auth-code warning is placed last as a guardrail. The enumeration of ten reason codes is somewhat verbose given an output schema exists, but each item carries disambiguation value, particularly the note that not_registered means 'register it instead'.

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?

Given a one-parameter batched tool with annotations and an output schema, the description covers everything an agent needs: batch limit, read-only nature, the meaning of the tri-state transferable field, and the pricing semantics. No gaps remain that would cause a misinvocation.

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 the single parameter is already documented, but the description adds useful meaning: each element is resolved against its own registry, which implies mixed TLDs are acceptable in one call, and it restates the 5-name ceiling as an operational limit. That is modest added value above 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 and resource — querying each name's registry for transferability — plus the secondary function of quoting the first-term transfer price in USD. This clearly distinguishes it from sibling tools that deal with availability (check_domain) or TLD policy (get_tld_requirements).

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 concrete usage boundaries: up to 5 names per call, read-only, and an explicit prohibition ('Never send a transfer authorization code here: the transfer itself asks for it') that routes the agent to a different action. It also hints at a follow-up path ('not_registered ... register it instead'). It stops short of naming sibling tools like check_domain for availability-only lookups, so it is clear context without explicit alternatives.

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 read-only and idempotent, and the description adds substantial context beyond them: a batch cap of 10 extensions, USD currency with the ICANN fee included, the premium-pricing caveat that standard prices can understate a specific name's cost, and the tld_not_found failure mode. That is exactly the kind of surprise-prevention detail an agent needs before quoting a price.

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 with the purpose front-loaded and the price/premium caveat placed where it matters. It is on the long side, but essentially every clause corresponds to a distinct returned field or a behavioral caveat, so little is wasted.

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?

Rich annotations and an output schema carry the structural load, and the description still supplies the operational knowledge an agent needs: batch limits, currency, premium-price escalation path, and the not-found outcome. Nothing required to call it correctly or interpret results 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% and the schema already explains the no-dot format, so baseline would be 3. The description earns a bump by restating the 10-per-call ceiling and illustrating expected inputs (.app, .dev, .us) in the context of what they imply about the returned data.

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 ('look up what OrbitFour charges and requires for domain extensions') and enumerates the returned data: prices, term lengths, WHOIS privacy, eligibility, https_required, and registration JSON Schemas. This is clearly distinguishable from the sibling tools, which operate on individual domains rather than the TLD-level ruleset.

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?

Provides a concrete routing rule: when premium_possible is true, the specific name must be quoted with check_domain, and unknown extensions return tld_not_found. It does not state when to prefer check_transfer or search_domains, but the split between TLD-level rules and domain-level checks is clear enough to act on.

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 idempotent, so the safety profile is covered; the description adds that results come from a live check, include 'taken and unknown' statuses, may be unordered/filtered (left_out, unchecked_names), and that the search is advisory only. The final 'Read-only, no side effects' sentence merely restates the annotations, which caps 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?

The purpose is front-loaded, which is good, but the body is two enormous run-on sentences chaining together output-field explanations; the density makes it harder to scan than necessary. It is not padded with fluff, but the structure could be split so an agent can locate the top_picks vs suggestions distinction quickly.

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 6 parameters, full schema coverage, an output schema and rich annotations, this description already carries more than the minimum, and the advisory/purchase caveats are genuinely important context for a domain-search tool. It over-explains return fields that the output schema already documents, so it is complete but slightly redundant rather than optimally scoped.

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 already 100%, so baseline is 3, but the description adds real meaning: 'up to limit ranked names', 'never repeating a top pick', per-year USD pricing tied to years, and that each entry in tlds becomes a top pick and reports why it found nothing. That goes beyond the schema field text for tlds, limit and include_premium.

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 ('Find domain names') plus the input shape it accepts (free-text idea, brand, phrase) and the derivation rule (short combinations of its words). It also names the sibling it complements — 'confirm the chosen name with check_domain' — so an agent can separate search from single-name verification without opening another 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 clear when-to-use framing (starting from a free-text idea rather than a known domain) and an explicit handoff rule to check_domain before quoting, plus the note that a purchase re-checks. It stops short of naming when NOT to use it — e.g. checking one already-known domain, or the check_transfer/get_tld_requirements siblings — so the exclusions are inferred rather than stated.

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