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

Annotations include destructiveHint=false, idempotentHint=false, openWorldHint=true. The description adds value by noting that the response includes a 'resolved_domain' in ASCII format, which is beyond the schema. However, it does not detail other behavioral aspects like validation 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 long, front-loads the primary purpose and supported types, and includes a specific response detail. No extraneous 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 complexity (6 parameters, 4 required, no output schema), the description is adequate but could mention potential conflicts (e.g., duplicate records) or propagation behavior. The presence of sibling tools partially compensates.

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 each parameter is already documented. The tool description does not add new semantic information about parameters beyond listing types. 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 that the tool creates a new DNS record and lists the supported record types (A/AAAA/CNAME/MX/TXT/SRV/CAA). It distinguishes from sibling tools like delete_dns_record and update_dns_record by focusing on creation.

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 adding a new DNS record but does not explicitly state when to use it versus alternatives (e.g., update_dns_record for modifications, delete_dns_record for removal). No when-not or exclusion 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 (non-destructive, non-idempotent, open-world) are supplemented with useful behavioral details: automatic domain ownership verification via TXT record and the ASCII format of resolved addresses in the response. 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 extremely concise, consisting of two sentences that cover purpose and key behavioral context without any 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?

Given moderate complexity (4 parameters, no output schema), the description covers essential behavioral context (automatic verification and response format). However, it omits details about the full response structure or potential errors, 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?

Schema description coverage is 100%, with each parameter having adequate descriptions (e.g., mail_address normalization). The tool description adds no additional parameter semantics, so the 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 states the tool creates a new mail account, specifying the verb and resource. However, it does not explicitly differentiate from the sibling 'create_mail_account_with_verification', which may cause confusion since both seem to involve verification.

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?

No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives like 'create_mail_account_with_verification', nor does it mention prerequisites or exclusions.

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 provide openWorldHint: true and destructiveHint: false. The description adds significant behavioral detail: it includes TXT authentication, DNS propagation wait, retries up to verification_wait_ms, and normalization of Japanese domains to ASCII. 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?

Two concise sentences with no fluff. The description is front-loaded with the core purpose and efficiently covers the automation flow and domain normalization.

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 internal flow well, but does not mention what the tool returns (e.g., success confirmation, account ID). Since there is no output schema, the description should provide some output expectations. Missing this information reduces completeness for agent 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%, so baseline is 3. The description adds context for verification_wait_ms (total wait limit) and poll_interval_ms (retry interval), but does not explain other parameters beyond what the schema already provides. Does not improve understanding significantly.

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 purpose: a high-level tool that automates domain verification and DNS propagation wait before creating a mail account. It uses specific verbs (内包, 自動実行) and distinguishes itself from siblings like create_mail_account and ensure_domain_verified by being the composite flow.

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 guides usage by explaining the automated steps (existing check, ensure_domain_verified, POST /mail with retries). It contrasts with simpler tools like create_mail_account, but does not explicitly state when to use this tool over 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?

The description adds value beyond the destructiveHint annotation by explicitly stating the operation cannot be undone and mandating confirm=true. This provides useful behavioral context.

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 concise sentences, front-loaded with verb+resource, and every word earns its place. Zero waste.

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 destructive tool with two required parameters, the description is complete. It covers purpose and critical constraint, though could optionally state that the record is permanently removed.

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 baseline is 3. The description reiterates the confirm requirement but adds no new meaning 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 clearly states the action ('delete') and resource ('DNS record'), distinguishing it from sibling tools like create_dns_record and 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?

The description specifies that the action is irreversible and requires confirm=true, providing clear context for when to use. However, it does not explicitly exclude alternative tools or mention prerequisites.

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. The description adds value by stating the operation is irreversible and that confirm=true is required, which goes beyond the annotation. It does not contradict the idempotentHint or openWorldHint.

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, front-loading the action and key constraint (irreversibility, confirm=true). 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 destructive tool with annotations present, the description covers the essential behavior and safety requirement. It does not describe return values (no output schema) or side effects, but the openWorldHint suggests possible extras. Adequate for the complexity.

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 for both parameters (mail_address with normalization hint, confirm as explicit consent) already cover 100%. The tool description echoes the confirm requirement but adds no new parameter semantics 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?

Description clearly states the action (delete) and resource (mail account). It also mentions irreversibility and the confirmation requirement, making it distinct from sibling tools like create_mail_account or update_mail_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 emphasizes that the operation cannot be undone and requires explicit confirmation (confirm=true). This provides clear usage context, though it does not explicitly compare with alternatives (there is only one delete mail tool).

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, openWorldHint=true), the description adds that it does nothing if the record already matches, does not wait for DNS propagation, and the response field 'resolved_domain' is the ASCII form. 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?

The description is two sentences with no wasted words. It front-loads the core action ('align TXT record') and efficiently conveys conditions and side effects.

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 one parameter and no output schema, the description adequately covers what it does, idempotent behavior, and a notable aspect (no wait for propagation). It is complete for effective usage.

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 single parameter 'domain' has a schema description covering 100% (Japanese domain support, automatic Punycode normalization). The tool description does not add further parameter details, 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 purpose: aligning the TXT record '_xserver-verify.{domain}' with the current domain validation token. It specifies the exact resource and action, and distinguishes from sibling tools like 'create_dns_record' which would generically create DNS records.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for domain verification but does not explicitly state when to use this tool versus alternatives (e.g., 'create_dns_record', 'update_dns_record'). It lacks guidance on prerequisites or exclusion scenarios, though the idempotent hint and open world hint provide some 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?

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is clear. The description adds value by specifying the returned fields (capacity, usage, memo) beyond the schema. However, it does not mention error cases or permissions.

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 sentence with no redundant words. Every part is meaningful.

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 tool with one parameter, the description covers the purpose and return fields. No output schema exists, but the description compensates. Could mention behavior if account not found, but overall adequate.

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, and the schema already describes it with ASCII normalization. The description does not add extra meaning beyond the schema, 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 clearly states the resource (mail account details) and the data retrieved (capacity, usage, memo). It distinguishes from siblings like list_mail_accounts (list all) and update_mail_account (update) by focusing on a single account's details.

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?

No explicit guidance on when to use versus alternatives (e.g., list_mail_accounts for listing all accounts). Usage is implied by the tool name, but the description lacks explicit when-not or alternative references.

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 (readOnlyHint, idempotentHint, openWorldHint) already indicate safe read behavior. The description adds the specific resource being queried but no additional behavioral traits like rate limits or return structure.

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 sentence with no filler, front-loaded with the verb '取得する' (retrieve), and efficiently captures the tool's 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 read tool with one parameter and detailed annotations, the description is largely complete. It mentions what settings are retrieved, though it could optionally describe the return format more explicitly.

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 description does not add meaning beyond what the schema already provides for the mail_address parameter. 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 tool retrieves forwarding settings for a specified mail account, including forwarding destination and mailbox retention. It succinctly distinguishes from sibling tools like update_mail_forwarding and create_mail_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 implies usage for viewing forwarding settings but does not explicitly compare with alternatives or mention when not to use. Given sibling tools, the purpose is inferred but not guided.

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 and openWorld, so safety is clear. The description adds value by listing the exact data returned (specs, version, name servers, domain validation token), providing behavioral 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?

The description is a single sentence, 20 words in Japanese, with no wasted words. It is front-loaded 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?

Given the tool has no parameters, no output schema, and annotations cover safety, the description is mostly complete. It lists what is returned, though it does not detail the format or any authentication requirements. Still, it is sufficient for a simple getter.

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 zero parameters and schema description coverage is 100%, so the description need not explain parameters. According to guidelines, baseline is 4, 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 uses the verb 'get' and lists specific resources: server specs, software version, name servers, and domain validation token. It clearly distinguishes from sibling tools which focus on DNS or mail operations.

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 use when server info is needed, but it does not explicitly state when not to use it or provide alternatives. For a parameterless getter, this is acceptable.

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 and openWorldHint, indicating safe read operation. The description adds concrete details about the data returned (disk usage, file count, resource counts), which is 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?

The description is a single, well-structured sentence that front-loads key information (what is retrieved) and is free of extraneous content. Every word 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 no output schema, the description explains the types of data returned (disk usage, file count, resource counts). While it could detail the exact fields or format, it is largely complete for a straightforward read-only statistics 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?

There are no parameters, so schema coverage is 100%. The description adds meaning by specifying what data is returned, which is sufficient. Baseline score of 4 for no-parameter tool.

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 explicitly states the tool retrieves disk usage, file count, and various resource setting counts (domains, emails, MySQL). This is a specific verb-resource combination that clearly distinguishes it from sibling tools which focus on managing individual DNS or mail 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?

No explicit guidance on when to use this tool versus alternatives. However, the description implies it is used for overall server usage statistics, and siblings are for specific resource management, making usage somewhat clear without direct instruction.

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 (readOnlyHint, openWorldHint), the description reveals the domain filtering behavior and automatic IDN normalization. This adds useful context about input processing. It does not mention output characteristics, but annotations cover safety and non-determinism.

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 concise sentences, front-loaded with the core purpose, then the parameter condition. No redundant information; every word 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?

For a simple list operation with one optional parameter and annotations covering safety and open world, the description is mostly complete. It specifies what records are listed and how to filter, though it omits details like return format or pagination, which are not critical but could be helpful.

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 parameter description already explains the domain is optional and for filtering, including IDN normalization. The tool description merely restates this, adding no new 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 tool lists DNS records from the server, and mentions optional domain filtering. The verb 'list' and resource 'DNS records' are specific. While it implicitly differentiates from sibling tools like create/delete/update, it does not explicitly distinguish from them, so not a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use the optional domain parameter but provides no guidance on when to use this tool versus alternatives (e.g., use this for viewing, not modifying). The usage context is implied but not explicit.

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 and idempotentHint=true, so the description adds no behavioral information beyond the domain filtering detail. It does not contradict annotations but adds minimal value beyond structured data.

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 short sentences, front-loaded with main action. No unnecessary words or redundancy. Efficiently conveys purpose and key optional behavior.

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 is adequate for a simple list tool with one optional parameter. It covers purpose and filtering. However, it does not mention output format, pagination, or limits, which might be relevant given openWorldHint=true. Missing minor detail that could 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?

Schema coverage is 100%, so the schema already describes the domain parameter with IDN normalization details. The description adds a brief summary of filtering functionality but no new semantics 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 it retrieves a list of registered mail accounts on XServer, with optional domain filtering. It uses specific verb 'list' and resource 'mail accounts', distinguishing it from siblings like get_mail_account (single) or create/delete/update (mutations).

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 context for when to use (list all or filter by domain) but does not explicitly mention alternatives or when not to use it. For example, it could note that for a single account, get_mail_account should be used. Lacks explicit exclusion guidance.

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 value beyond annotations by explaining the partial update behavior and the special response field 'resolved_domain' when domain is provided. Annotations already indicate non-destructive and idempotent hints, which are consistent. No contradictions found.

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 three sentences, each conveying important information without redundancy. It is front-loaded with the core action and efficiently adds details about partial update and a specific response behavior. 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?

Given the tool has 7 parameters and no output schema, the description covers the partial update behavior and a specific output field, but does not mention error cases, response format for other fields, or what happens if no optional fields are provided. Adequate but has gaps.

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 the schema already documents all parameters well. The description adds only a general note about partial update and resolved_domain, but does not provide additional semantics for individual parameters. 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 that this tool performs a partial update of a DNS record, specifying that only sent fields are overwritten while omitted fields retain current settings. The title 'Update DNS record' and the sibling tools (create, delete) make its purpose distinct.

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 that this tool should be used when you want to update only specific fields of a DNS record, as it performs a partial update. However, it does not explicitly state when not to use it or compare it to other tools like create_dns_record. Missing explicit alternatives guidance.

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 idempotentHint and openWorldHint. The description adds behavioral detail that omitted fields are not changed, which is consistent and adds context. No contradictions are present.

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 just two sentences, front-loaded with the core action, and no redundant information. Every word 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 output schema, the description does not explain return values, which is acceptable for a simple update. It adequately covers the input behavior and is supplemented by rich annotations and sibling 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% with detailed parameter descriptions. The tool description's note about preserving omitted fields adds general context, but it doesn't significantly enhance understanding of individual parameters 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 explicitly states 'partially update mail account settings' (メールアカウントの設定を部分更新する), clearly defining the verb and resource. It distinguishes itself from sibling tools like create_mail_account and delete_mail_account by emphasizing partial update.

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 context that omitted fields preserve current values, guiding an agent to only send changed fields. While it doesn't explicitly mention when not to use this tool, the sibling tool names imply its role for modification rather than creation or deletion.

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 and openWorldHint. The description adds valuable details like the clearing behavior for empty arrays and normalization of Japanese domains. It also notes that keep_in_mailbox is unchanged if omitted. This adds 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?

The description is a single sentence with an additional clarifying sentence. It is concise and front-loaded with the main action. However, it could be more structured with explicit usage notes.

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 operation and parameter effects but lacks information about return values, prerequisites (e.g., domain verification), or side effects. For a mutation tool with no output schema, this is adequate but not 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 slightly adds by repeating the clearing behavior, but this is already in the schema. No new parameter meaning is provided beyond what the schema already conveys.

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 (overwrite update) and resource (mail forwarding settings for a specified account), distinguishing it from sibling tools like get_mail_forwarding. It also specifies that passing an empty array clears all forwarding addresses.

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 it is for updating forwarding settings but does not explicitly state when to use it or when not to. No alternatives or exclusions are mentioned, leaving the agent without guidance on selecting this tool over siblings.

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