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

Beyond annotations (readOnlyHint, idempotentHint, openWorldHint), the description details the return fields (availability, registration price, renewal price, transfer price, premium details) and notes pricing is in USD. It also discloses behavioral implications of cost mismatch.

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 description is extremely concise: two sentences that deliver the purpose, key behavioral details, and usage guidance with zero waste. Information is front-loaded and efficiently structured.

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 single required parameter, full annotation coverage, and no output schema, the description provides complete context: it explains what the tool returns, how to use it, and a critical warning about registration rejection.

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% with a clear parameter description for 'domain'. The tool description does not add new information about the parameter beyond what the schema already provides, so a baseline score of 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 clearly states the tool checks domain availability and pricing, specifying the resource (domain) and the action (check availability and cost). It distinguishes itself from the sibling register_domain by mentioning it should be used before registration.

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?

Explicitly advises to use this tool BEFORE register_domain to confirm cost, citing that Porkbun rejects registrations with mismatched costs. Provides clear context for correct usage.

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 non-read-only, non-destructive, idempotent, open world. The description adds useful behavioral details: the tool is free (no credit cost) and returns the new record's id. No contradictions with annotations.

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 description is relatively brief (3 sentences) with the main purpose upfront. It conveys necessary information without excessive verbosity, though the information about name and prio could be more integrated but is still clear.

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 create tool with 6 parameters (3 required) and no output schema, the description covers key aspects: creation action, return value (id), cost, and important parameter nuances. It does not detail error handling or permissions, but given the rich schema and annotations, it is sufficiently complete.

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% with descriptions for each parameter. The description adds extra semantic guidance: explains name format (omit for apex, subdomain prefix only) and that prio is required for MX and SRV. This goes beyond the schema descriptions.

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 starts with 'Create a DNS record on a domain', clearly specifying the verb and resource. It distinguishes from sibling tools by mentioning the returned id can be used by update_dns_record and delete_dns_record.

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 clear context for usage: explains when to use (to create a DNS record), gives specific instructions for the name field (apex vs subdomain), and notes that prio is required for MX/SRV. States it's free, which aids decision-making. Lacks explicit when-not-to-use mentions.

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 description adds context beyond annotations (readOnlyHint=false, idempotentHint=true) by explaining the purpose (publish chain-of-trust) and required fields. No contradictions; the Submit action aligns with mutating 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?

The description is three concise sentences: function, usage scenario, and parameter summary. No extraneous information; front-loaded with the key purpose.

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?

The description adequately covers purpose, usage, and parameters. It could mention post-submission behavior or validation, but given the complexity and annotations, it is sufficiently complete.

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 baseline is 3. The description adds value by grouping parameters as required vs optional and noting that key-data fields are rare, which aids parameter selection.

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 states the tool submits a DNSSEC DS record to the registry for a domain. It distinguishes from siblings like create_dns_record by specifying DNSSEC and the use case of custom nameservers.

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 description explicitly says 'Use when you sign DNS yourself...' and lists required/optional fields, providing clear context. It does not explicitly state when not to use or give alternatives, but the scenario is well-defined.

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 include idempotentHint=true, and the description reinforces 'Idempotent.' It also adds behavioral detail beyond annotations: the subdomain must be only the host part, and IPs are an array of IPv4/IPv6 addresses. No contradictions.

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, each essential: purpose, usage case, and key parameter clarifications. No redundancy, well-structured, and front-loaded.

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?

The description covers purpose, usage, idempotency, and parameter semantics. It lacks explicit mention of behavior on existing records or error conditions, but for a simple creation tool with strong annotations, it is sufficiently complete.

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 baseline is 3. The description rephrases the subdomain and IPs details but does not add new parameter information beyond what the schema already provides.

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 states clearly that the tool creates a glue record for a host on a domain, and provides a specific use case (running own nameservers) that distinguishes it from sibling tools like create_dns_record.

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 description explicitly says when to use this tool (for nameservers on the same domain) and clarifies the subdomain format. It does not explicitly state when not to use it, but the context and sibling tools imply 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 indicate this is a non-destructive, idempotent mutation. The description adds only that it is 'free', which is tangential. No contradiction found; the description does not significantly extend behavioral insight beyond annotations.

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 concise sentences front-load the core action, add scope specifics, and provide a use case and cost. Every sentence adds value with no redundancy.

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?

The tool has no output schema and the description does not mention return values, error behavior, or confirmation. For a creation tool with multiple parameters, this is adequate but leaves room for more context about expected results.

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 baseline is 3. The description mentions that omitting subdomain targets the apex, but the schema already describes this. No new parameter-level information is added beyond what the schema provides.

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 states it adds a URL forwarding rule for a domain, specifies the scope (subdomain or apex), and distinguishes from sibling tools like create_dns_record or delete_url_forward by describing a specific use case (redirects without a web server).

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 description implies when to use (redirects without a web server) but does not explicitly state when not to use or compare with alternatives. Sibling tools cover DNS records, so the context is clear but lacks explicit exclusion.

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?

As annotations already provide destructiveHint, idempotentHint, and openWorldHint, the description adds value by explicitly stating idempotent behavior (deleting already-deleted returns success) and that it is free, which are not captured by annotations.

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 description is two sentences, front-loaded with the action, and contains no redundant information. Every sentence serves a clear purpose.

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 simple tool with two parameters, the description is largely complete, mentioning idempotency and cost. It could optionally clarify behavior for non-existent IDs beyond already-deleted, but this is minor.

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% with clear parameter descriptions. The description adds the context that record_id comes from list_dns_records, which aids the agent in understanding the parameter's origin 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?

The description clearly states the verb 'Delete', the resource 'single DNS record', and specifies the source of the record_id, distinguishing it from other delete tools like delete_dnssec_record or delete_glue_record.

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 description implies usage by describing the action, but it does not explicitly state when to use this tool versus alternatives like update_dns_record or other delete tools. No when-not guidance is provided.

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 indicate destructiveHint=true and idempotentHint=true. The description adds valuable detail: 'Idempotent: deleting a non-existent key tag returns success,' which aligns with annotations and provides extra behavioral clarity.

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 action and purpose. Every word earns its place. No fluff or redundant 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?

The description covers the main action and idempotency, but lacks details about prerequisites (e.g., domain must exist, DNSSEC enabled) and return behavior. Given the simplicity and no output schema, it is minimally adequate but not comprehensive.

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% with descriptions for both parameters. The description mentions 'key tag from list_dnssec_records,' but this is already implied in the schema. No additional parameter meaning 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?

The description clearly states the action (remove), resource (DNSSEC DS record), and context (identified by key tag, used when retiring a key). It distinguishes from siblings like create_dnssec_record and list_dnssec_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?

The description explicitly says 'Use when retiring a key,' providing a clear use case. However, it does not mention when not to use or list alternatives, but the context is specific enough for most agents.

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 indicate destructiveHint=true and idempotentHint=true. The description adds useful context by explicitly stating that deleting a non-existent glue record returns success, which explains the idempotent behavior beyond the annotation flag.

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 description is extremely concise with two sentences, no redundant words, and front-loads the main action. Every sentence serves a purpose: stating the function and clarifying idempotency.

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 the simplicity of the tool (2 required parameters, full schema coverage, annotations present, no output schema), the description adequately covers purpose and idempotency. Minor missing details like error behavior on invalid domain are acceptable for this scope.

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?

The input schema already fully describes both parameters (domain and subdomain) with clear descriptions. The description does not add any additional meaning or usage details for the parameters, so it meets the baseline for full schema coverage.

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 states 'Delete a glue record by host on a domain', providing a specific verb (delete) and resource (glue record). This distinguishes it from sibling tools like create_glue_record or list_glue_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?

The description offers no guidance on when to use this tool versus alternatives, such as prerequisites or context for deletion. It does not mention when not to use it or compare to other deletion or record tools.

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 indicate destructive and idempotent. Description adds context about the source of the record_id, but does not contradict annotations. No additional side effects disclosed beyond the standard deletion implied by destructiveHint.

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?

Extremely concise: one sentence conveying action, identifier source, and idempotency. No unnecessary words.

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 delete tool with no output schema, the description, combined with annotations, provides sufficient information: what it does, how to get the required ID, and idempotency. No missing context.

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 described adequately in the schema. The description reinforces the source of record_id but adds no new meaning beyond that.

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?

Clearly states action (delete), resource (URL forwarding rule), and source of identifier (list_url_forwards). Distinguishes from sibling tools like create_url_forward and list_url_forwards.

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?

Explicitly mentions that the id comes from list_url_forwards, providing clear context for when to use. Idempotent hint reassures safe retries, but no explicit alternatives or when-not-to-use.

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 indicate readOnly and idempotent. The description adds value beyond these by specifying that amounts are in cents and that register_domain will be hard-blocked if over limit, which is relevant behavioral context for the agent.

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 main action, no wasted words. Perfectly sized for a simple tool.

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 the tool's simplicity (0 params, no output schema), the description covers what it returns, units, and usage context, leaving no obvious gaps for an agent.

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 and 100% schema coverage (empty schema), the description fully compensates by detailing the exact data returned (monthly spend limit, low-balance alert threshold, etc.), adding meaning that the schema lacks.

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 states it retrieves the API spend control configuration (specific resource), lists the returned fields, and explicitly distinguishes itself from siblings by linking to register_domain, which is a key consumer of this data.

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 advises using this tool before expensive operations and gives register_domain as an example, but does not explicitly mention when not to use or compare with alternatives like get_balance.

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, idempotentHint, and openWorldHint. The description adds valuable behavioral context by explaining the return format (integer cents and display string) and the intended use case, which goes beyond what annotations provide. No contradictions.

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 description consists of two concise sentences that front-load the main action and return format, with no wasted words. Every sentence serves a purpose.

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 no parameters and no output schema, the description fully explains what the tool returns and why to use it. The context is complete for a simple read-only balance check tool.

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?

The tool has no parameters, and schema coverage is 100% (no parameters to document). The description does not need to add parameter semantics, and the baseline score of 4 applies since there are no parameters and no omissions.

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 states the tool retrieves the available account credit balance for the authenticated Porkbun account, specifies the return format (cents and display string), and distinguishes its purpose from sibling tools by noting it is used to check spend headroom before registrations or renewals.

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 description explicitly states when to use this tool ('check spend headroom before initiating registrations or renewals'), providing clear context. It does not explicitly list when not to use it or mention alternatives, but the guidance is sufficient for agent decision-making.

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 declare readOnly, idempotent, and openWorld hints. The description adds that it returns specific metadata fields and an error code if domain not found, providing useful behavioral context beyond the annotations.

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 purpose, then lists key fields and an error condition. No wasted words; every sentence adds value.

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 2 parameters, no output schema, and good annotations, the description sufficiently covers the tool's behavior. It could mention the response format, but the annotations and schema make it complete enough for correct invocation.

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% with both parameters described. The description mentions 'domain' and 'include_labels' implicitly but adds no extra detail beyond the schema, so meets baseline.

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 states the tool retrieves metadata for a single domain, listing specific fields like status, TLD, dates, etc. It distinguishes from list_domains (multiple domains) and check_domain (likely availability) by focusing on 'a single domain in the authenticated account'.

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 description implicitly indicates when to use (to get details of a specific domain you own) and explains the error condition for nonexistent domains. However, it does not explicitly contrast with siblings like check_domain or list_domains, leaving some ambiguity.

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, idempotentHint, and openWorldHint. The description adds that it 'Returns an array of nameserver hostnames', which is a minor behavioral detail beyond the annotations. No contradiction.

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 description is two sentences, front-loading the core purpose, and contains no extraneous information. It is highly efficient for the agent.

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 simple read-only tool with one parameter and no output schema, the description adequately covers the return type (array) and the relationship to update_nameservers. It implicitly covers the domain requirement by mentioning 'authenticated account'.

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% with a detailed schema description for the 'domain' parameter. The description does not add additional parameter meaning beyond what is already in the schema, so a baseline of 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 clearly specifies the verb 'Get', the resource 'nameservers configured for a domain', and the scope 'in the authenticated account'. It also distinguishes itself from the sibling 'update_nameservers' by noting it is the read-only counterpart.

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 description states it is a 'read-only complement to update_nameservers', which implies the appropriate context (viewing vs. modifying). However, it does not explicitly list when not to use or provide alternatives beyond that sibling.

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, idempotentHint, and openWorldHint. The description adds valuable context: no authentication required and that pricing is standard only. This aligns with annotations and provides additional behavioral insight.

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 cover all necessary information with no fluff. The most important details are front-loaded.

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 zero parameters and no output schema, the description fully explains purpose, usage guidance, and limitations. It is complete for an agent to decide when and how to invoke.

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?

There are no parameters, so description cannot add meaning beyond schema. Baseline for 0 parameters is 4, and the description does not need to elaborate.

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 states the tool retrieves current Porkbun pricing for all supported TLDs, specifying registration, renewal, and transfer prices. This is a specific verb and resource, and it distinguishes from sibling tools like check_domain by noting that premium domains are handled separately.

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?

Explicitly states when to use (comparing TLD costs before registering), provides exclusions (premium domains), and names an alternative tool (check_domain). Also notes that no authentication is required.

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 indicate readOnly, idempotent, openWorld. Description adds that it returns certificate chain, private key, and public key as PEM strings, and explains Porkbun's automatic provisioning, which is valuable context beyond annotations.

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, no filler, front-loaded with action. Every sentence adds value.

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 low complexity (1 param, no output schema), the description covers purpose, return values, and background, making it complete for an AI agent.

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 already fully describes the single parameter 'domain' with 100% coverage. Description implicitly references it but adds no new detail 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?

The description clearly states the verb 'Retrieve' and the resource 'free Porkbun-issued SSL certificate bundle for a domain', distinguishing it from sibling tools that manage DNS or domains.

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 description says 'Use this to install TLS on a server you control', providing clear context for when to use. It does not explicitly exclude alternatives, but the guidance is sufficient.

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?

Adds behavioral info beyond annotations: returns same status values as list_transfers plus human-readable description. Annotations already indicate read-only, idempotent, open-world; description complements well.

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: first states purpose, second adds usage context and output info. No fluff, highly efficient.

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?

Fully covers purpose, usage context (polling after transfer), and output (status values plus description). No output schema, but description explains what to expect. Adequate for a simple 1-param read tool.

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 description for domain parameter matches schema description exactly. Description adds no new semantics beyond what's in the input 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?

Description clearly states verb 'Get', resource 'status of a specific inbound transfer for a domain'. Distinguishes from sibling tools like list_transfers (which lists all).

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?

Explicitly recommends polling after transfer_domain, with typical window (5-7 days). Could mention alternatives like list_transfers but context is clear.

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, idempotentHint, and openWorldHint. The description adds value by detailing the returned fields (id, type, name, content, ttl, priority) and clarifying the `name` field behavior. No contradictions with annotations.

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 description is two sentences, front-loaded with the purpose and return info, and every sentence adds value. No wasted words.

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 simple list tool with no output schema, the description covers return fields and a note on the `id` field. It lacks pagination or ordering details, but given the likely scale of DNS records per domain, this is acceptable.

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% with a description for `domain`. The description adds minimal extra meaning beyond the schema (e.g., 'in the authenticated account'), but this is not parameter-specific. 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 clearly states the verb 'List' and the resource 'all DNS records for a domain', and distinguishes from sibling tools like create/delete/update DNS records and other list tools (e.g., list_dnssec_records) by specifying the scope.

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 description implies when to use (to view DNS records) and notes that the `id` field is needed for editing/deleting, providing context for alternative actions. It does not explicitly exclude other list tools but is clear enough for the primary use case.

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, idempotentHint=true, and openWorldHint=true, so the description does not need to reaffirm safety. It adds value by specifying the return fields (key tag, algorithm, digest type, digest) and the meaning of an empty array.

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 description is only two sentences, front-loaded with the action and resource. Every sentence adds value with no redundancy or wasted words.

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 simple tool with one parameter and no output schema, the description adequately describes the return fields and the meaning of an empty array. It lacks error conditions but is sufficient for a list operation.

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% for the single parameter 'domain', which is described as 'Fully qualified domain name, e.g. example.com'. The description does not add additional parameter information beyond what the schema provides, so 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 starts with 'List the DNSSEC DS records currently submitted to the registry for a domain', providing a specific verb (list), resource (DNSSEC DS records), and scope (for a domain). It clearly distinguishes from sibling tools like list_dns_records and create_dnssec_record.

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 description states 'Use this to verify DNSSEC chain-of-trust setup', giving a clear use case. It also explains that an empty array means not configured. It does not explicitly exclude alternatives but context implies usage for DNSSEC verification.

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 declare readOnlyHint and idempotentHint; description adds transparency about pagination (up to 1000 per page), return metadata fields, and filter semantics. No contradiction with annotations, which already cover read-only 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?

Well-structured with a clear opening sentence and a bulleted list of filters. While slightly lengthy, every sentence adds meaning and avoids redundancy.

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?

Despite no output schema, the description comprehensively covers return metadata, pagination limits, and all 10 parameters with optional filters. Differentiates from sibling tool and addresses common use cases adequately.

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?

Input schema covers 100% of parameters with descriptions. The description adds contextual value beyond schema, such as noting that api_access filter eliminates downstream errors and that expiring_within_days is useful for renewal automation.

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 states the tool lists domains in the authenticated Porkbun account, specifies return metadata (expire date, auto-renew, etc.), and distinguishes from the sibling tool get_domain for single-domain lookup.

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 explicit guidance on when to use this tool vs. get_domain for single domains, and explains each filter's purpose (e.g., api_access prevents errors). Does not explicitly compare to all siblings but offers sufficient context for common use cases like renewal automation.

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 indicate readOnlyHint, idempotentHint, and openWorldHint, so the bar is lower. The description adds valuable behavioral context by specifying the exact return fields (host, IPv4 addresses, IPv6 addresses), which is beyond what annotations provide. No contradiction.

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 description is concise (three sentences), front-loaded with the core action, and efficiently explains the concept of glue records. Every sentence adds value without unnecessary verbosity.

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 simple list tool with one required parameter and no output schema, the description fully covers the purpose, return values, and provides an example. It is complete and well-suited for agent selection.

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% with the domain parameter well-described. The description does not add additional meaning beyond confirming the domain context, so baseline score of 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 clearly states the tool's action ('List glue records for a domain') and explains what glue records are and what the tool returns (host, IPv4, IPv6). It effectively distinguishes from sibling tools like create_glue_record or delete_glue_record.

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 description implicitly communicates when to use this tool (when you need to view glue records), but it does not explicitly provide when-not-to-use scenarios or alternatives. The contrast with create/delete/update is clear from the sibling list.

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 declare readOnlyHint=true and idempotentHint=true, which the description aligns with by describing a read-only browse operation. The description adds valuable behavioral details: server-side filters, pagination limits (1000 with filters, up to 5000 without), and return fields. No contradiction.

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 description is well-structured with a clear opening sentence stating purpose, followed by return fields, then detailed parameter explanations. Every sentence is informative and no fluff. Front-loaded with the most critical 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?

Given the tool has 8 optional parameters and no output schema, the description covers purpose, parameter details, and behavioral differences. It omits explicit error handling or rate limits, but the read-only and idempotent annotations reduce the need. The return fields are mentioned, so it is mostly complete.

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 100% schema coverage, baseline is 3. The description adds meaning beyond the schema by explaining the query substring semantics (including exclusion with '-'), pagination modes (with vs. without filters), and sort defaults. This adds value, hence a 4.

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 states it is for browsing domains for sale on the Porkbun marketplace, distinguishing it from related tools like list_domains (which likely lists owned domains) and check_domain (availability). It explicitly mentions 'aftermarket — domains owned by other users, not new registrations' and lists the returned fields.

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 description implies usage for searching/sorting aftermarket domains and explains filter behavior (with filters vs. without). However, it does not explicitly state when not to use it or name alternative tools for other domain operations, though the clarity of purpose compensates.

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, idempotentHint, and openWorldHint. The description adds value by specifying the return structure (domain, status, create date) and listing example statuses, exceeding what annotations provide. No contradictions.

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 description is two concise sentences. It front-loads the main action and then provides return details and a usage hint. No unnecessary words.

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 the tool's simplicity (no parameters, no nested objects), the description fully covers what an agent needs: what it does, what it returns, and when to use it. No output schema exists, but the return fields are described adequately.

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 and 100% schema coverage, the description needs no parameter details. Baseline 4 applies per instructions; the description focuses on the tool's purpose, which 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 clearly states the tool lists all in-progress and recent inbound domain transfers, using a specific verb and resource. It distinguishes itself from sibling list tools like list_domains by focusing on transfers.

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 description explicitly says 'Use this to monitor transfers initiated by transfer_domain', providing a clear usage context. However, it doesn't mention when not to use it or alternatives like get_transfer_status for specific transfers, leaving a slight gap.

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, idempotentHint, and openWorldHint. The description adds the output structure but no additional behavioral traits like pagination or rate limits. With annotations covering safety, a score of 3 is appropriate.

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: first states purpose, second details entry contents. No redundancy, straight to the point.

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?

The description explains the output structure well despite no output schema. However, it lacks mention of pagination or sorting, which would improve completeness.

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?

The schema has 100% coverage with a description for the 'domain' parameter. The tool description does not add significant meaning beyond the schema's 'Fully qualified domain name' 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?

The description clearly states the tool lists URL forwarding rules for a domain, and specifies the contents of each entry including 'id' used by sibling 'delete_url_forward'. It distinguishes from other list tools.

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?

Description provides clear context for when to use (list all URL forwards for a domain) and cross-references the 'id' field with 'delete_url_forward'. However, it does not explicitly exclude alternative tools or scenarios.

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. Description adds that it returns public IP and API key validity, and that it is a verification tool.

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 purpose, no redundant 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?

For a tool with no parameters and no output schema, the description is complete: it states purpose, return values, and usage context.

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?

No parameters; description adds meaning by explaining what the tool returns (public IP, API key validity), which is not 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?

Description clearly states verb 'Verify' and resource 'Porkbun API connection and credentials', and distinguishes from sibling tools (all domain/DNS management) by being a health check.

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?

Explicitly states when to use: 'Use this as a first sanity check before making other calls.' Provides clear context.

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?

Adds critical context beyond annotations: 'Spends account credit,' cost mismatch rejection, idempotency details (24-hour retries), and registration limitations. Annotations indicate idempotentHint=true and openWorldHint=true, which the description corroborates and enriches.

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?

Single paragraph with no fluff. Uses bold for key warning ('Spends account credit'). Information is logically ordered: warning, action, parameter constraint, workflow, idempotency, limitations, prerequisites. Every sentence adds value.

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?

Covers most practical concerns: prerequisite checks, idempotency, domain limitations. Lacks description of return value (no output schema), but this is a payment tool where response is likely standard. Minor gap for full completeness.

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% with detailed parameter descriptions. The description adds workflow context (check_domain first, years multiplier) but does not significantly enhance semantic understanding beyond what the schema provides. 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 uses a specific verb ('Registers') and resource ('domain on the authenticated Porkbun account'), clearly distinguishing from sibling tools like check_domain (checking availability) and renew_domain (renewing an existing 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?

Explicit workflow: call check_domain first, confirm with user, then call this. States when NOT to use (premium domains, .uk, etc.) and prerequisites (verified email/phone, prior registration). Provides clear guidance on idempotency and retries.

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?

Adds critical context beyond annotations: spends account credit, idempotency with 24-hour retry window, error condition RENEWAL_TOO_SOON, premium domain exclusion. Annotations already indicate idempotent and not read-only/destructive.

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?

Front-loaded with a bold warning about spending credit, then clear purpose, then constraints. Each sentence adds value without redundancy.

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?

Covers preconditions, error behavior, and idempotency well. No output schema, so lack of return format info is minor; tool is action-oriented.

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 schema descriptions already state cost must match check_domain. Description reinforces this but adds domain API opt-in requirement (not parameter-specific). Little new parameter-level meaning beyond 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?

The description clearly states it renews an existing domain, distinguishes from sibling tools like register_domain, transfer_domain, and update_auto_renew.

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 specific conditions for use: must match price from check_domain, domain must be API-opted-in, cannot renew too soon, premium not supported. Lacks explicit alternatives but gives clear context.

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?

Adds critical behavior not in annotations: spends credit, async with 5-7 day delay, cost matching requirement, TLD restrictions. No contradiction with annotations.

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?

Every sentence adds value. Front-loaded with the most important note (spends credit). Structure is clear and efficient.

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?

Covers return value (transferId), polling advice, prerequisites, restrictions, and idempotency. No output schema, but description provides sufficient context for a mutation tool.

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 descriptions cover basics, but description adds must-match constraint for cost and emphasizes auth code requirement, improving parameter understanding.

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?

Clearly states it initiates a domain transfer, spends account credit, and returns a transferId. Distinguishes from siblings like check_domain and get_transfer_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?

Explicitly says to poll with get_transfer_status, warns about TLD restrictions (.uk etc.), and specifies prerequisites (auth code, cost matching check_domain).

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?

Beyond annotations (idempotentHint=true), the description adds that turning auto-renew on charges account credit, and turning it off requires manual renewal. This provides valuable behavioral context not present in annotations.

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 short sentences, no redundancy. The first sentence states purpose, the second explains consequences, and the third states idempotency. Every sentence earns its place.

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?

The tool is simple with only two parameters and clear behavior. The description covers purpose and consequences, but lacks information about return values or prerequisites (e.g., domain must exist). Still sufficient for the simple operation.

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 described in the schema. The description does not add additional meaning beyond the schema's descriptions, so baseline score of 3 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?

The description uses a specific verb ('Turn auto-renewal on or off') and resource ('for a domain in the authenticated account'), clearly distinguishing it from sibling tools like register_domain or update_dns_record.

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 explains the consequence of auto-renew being on (automatic charge) and off (manual renewal), giving context for when to toggle. It doesn't explicitly state when not to use it, but the context is clear.

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 provide idempotentHint=true and destructiveHint=false. The description reinforces idempotency ('applying the same update twice is a no-op') and adds the partial-update behavior, which provides additional context beyond annotations.

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, each serving a distinct purpose: stating the action, explaining partial updates, and noting idempotence. No superfluous words.

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?

The description lacks information about the return value (e.g., whether it returns the updated record or a success status). While the tool is simple and annotations cover safety, the absence of output schema makes this a noteworthy 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 has 100% parameter description coverage. The description adds value by explicitly stating that all fields except record_id and domain are optional and that record_id comes from list_dns_records, which helps the agent understand parameter usage without repeating schema details.

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 states the tool updates a DNS record, specifying the record_id and its source (list_dns_records). This distinguishes it from create, delete, and other update tools among siblings.

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 description specifies that only the fields to change should be passed, and that the operation is idempotent. While it doesn't explicitly exclude alternatives, the context (sibling tool names) and partial-update guidance are clear enough for the agent.

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?

Beyond annotations (idempotentHint=true, destructiveHint=false), the description adds behavioral context: it replaces the full IP list. This is critical for correct usage. However, it doesn't detail side effects or error conditions.

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 description is two sentences, concise and front-loaded. Every sentence adds value: the first states the purpose, the second clarifies behavior. No unnecessary text.

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 the low complexity (3 parameters, no output schema), the description is largely complete. It covers the core behavior, though it could benefit from noting that the record must exist or error handling.

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?

Input schema covers all parameters with descriptions (100% coverage). The description reinforces the replacement behavior for 'ips', but adds no new semantic information 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?

The description clearly states the action 'Update the IP addresses associated with an existing glue record' with the specific resource 'glue record'. It distinguishes from sibling tools like 'create_glue_record' and 'delete_glue_record' by focusing on modification of existing 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?

The description provides clear guidance on usage: 'pass all IPs you want set, not just additions' and 'Idempotent'. It implies usage when updating an existing glue record, but does not explicitly state prerequisites or when not to use it.

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 mark destructiveHint=true and idempotentHint=true. The description adds value by explaining the full replacement semantics, the consequence of disabling free DNS hosting, and a plain-language idempotency statement that reinforces the annotation without contradiction.

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 concise sentences, each serving a purpose: stating the action, clarifying the replacement nature with constraints, and noting idempotency. No redundant or missing 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?

Given the tool's simplicity (2 required params, no output schema), the description covers all needed behavioral and usage aspects. The side effect of disabling free DNS hosting is a valuable addition that ensures complete understanding.

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% with both parameters described. The description adds semantic value for nameservers by clarifying it is a full replacement and explaining the 2-13 entry requirement beyond the schema's range constraints. Domain parameter adds no extra semantics, but overall the description enhances understanding.

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 specifies the action 'Replace the nameservers for a domain' with a clear verb and resource. It distinguishes from read-only siblings like get_nameservers by emphasizing replacement, and explicitly states it is not an append.

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 description provides usage context: full replacement (not append), TLD constraints (2-13 entries), and side effect (disabling free DNS hosting). It does not explicitly compare to sibling tools or state when not to use, but overall guidance is clear.

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