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

With no annotations, the description must carry the behavioral burden, but it merely says 'add' and gives no effect, permission, reversibility, or preview behavior. The schema's dryRun parameter defaults to true (preview, no update), which means the tool does not actually add by default; the description could mislead an agent expecting an immediate mutation.

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 text is a single concise sentence with no filler, so it earns the middle score. It is also too terse to do more than state the basic action, leaving key operational context unstated.

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?

A 7-parameter mutation tool with no annotations and no output schema needs far more context than one sentence. The description omits the meaning of INTERNATIONAL, how dryRun prevents real changes, and how filter/policyId/additionalCost relate to the operation, so an agent cannot reliably invoke the 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 description coverage is 100%, so the baseline is 3 even though the description itself adds no parameter details. The schema already documents service, cost, shipTo, dryRun, filter, policyId, and additionalCost, so the description does not need to repeat them.

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 the action ('追加' = add) and the object (shippingService), and narrows the target to 'INTERNATIONAL', which is enough to distinguish it from sibling remove/reorder/list actions. However, 'INTERNATIONAL' is not defined as a destination, policy, or zone, so the scope remains slightly ambiguous.

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 guidance is given about when to use add_shipping_service versus remove_shipping_service, reorder_shipping_services, or list_shipping_services. The intended context is only implied by the tool name and the single word 'INTERNATIONAL'.

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?

With no annotations, the description must carry full disclosure burden. It does reveal that linked listings cause a failure report, but it omits other critical behavior such as permission requirements, whether deletion is atomic or partial, reversibility, or what the report contains. This is a significant gap for a mutation 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?

A single sentence that front-loads the action and immediately states the key caveat about linked listings. Zero filler, 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 bulk delete with a dryRun flag and failure reporting, the description is incomplete. It doesn't explain the report format, what happens on partial success, behavior for invalid IDs, or the semantics of dryRun beyond the schema. No output schema exists to compensate, so the description must carry this information but does not.

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% because both dryRun and policyIds have descriptions in the schema. The tool description adds no additional parameter meaning beyond what the schema already provides, so the baseline 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 states a specific verb-resource pair ('bulk delete multiple fulfillment policies') and a distinctive behavioral condition (linked listings are reported as failures), which clearly separates it from the single-delete sibling delete_policy and other 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?

The description and name make it clear this is for bulk deletion, but it never explicitly contrasts with delete_policy for single deletions or mentions when to choose one over the other. Context implies it, but no explicit exclusion is given.

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?

With no annotations, the description must disclose risk and side effects, but it only restates that an update occurs. It says nothing about dryRun defaulting to true, the actual write when dryRun=false, whether matching exclusions are replaced or merged, or irreversibility—serious omissions for a mutation 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?

One short phrase conveys action, resource, bulk scope, and the matching mechanism, with the key 'bulk + filter' information front-loaded. No filler or redundancy; every element 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?

Although the schema richly explains all parameters, the description itself offers only purpose, with no guidance on safe execution (dryRun preview), side effects, or fallback to update_exclusions, and there is no annotation or output schema to fill those gaps. An agent can identify the tool but not confidently reason about what applying the updates will do.

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 baseline applies: the schema fully documents dryRun, filter, addExclusions, and removeExclusions. The description adds only the filter's partial-match aspect, which duplicates schema content and does not compensate for anything.

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 combines a specific verb (更新/update), resource (除外設定/exclusion settings), and scope (一括/bulk via policy-name filter), clearly distinguishing it from the singular update_exclusions and read-only get_policy_exclusions siblings. Even without a title, the action and filter mechanism are unmistakable.

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 'bulk' + 'policy name filter' phrasing implies this is for updating many policies at once, and the sibling name update_exclusions signals the singular alternative. However, no explicit when-to-use, when-not-to-use, or alternative routing is provided; the usage guidance is left to inference.

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?

With no annotations, the description carries the burden of behavioral disclosure. It states the core action (clone) and the optional exclusion modifications, but does not explain the interaction between add/remove/set parameters, nor any side effects (e.g., whether the source is modified, or what the tool returns). It adds basic context but leaves significant behavioral details uncovered.

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, front-loaded sentence that states the primary purpose first and adds a secondary capability. There is no redundant information or filler. It is appropriately sized 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?

The tool has 5 parameters and no output schema, and no annotations. The description is minimal and does not explain the combined behavior of the exclusion parameters (e.g., whether the clone inherits the source's exclusions, or how add/remove interact). It also does not mention what the tool returns (e.g., new policy ID) or any error conditions. Given the complexity, this is a significant 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 coverage is 100%, so each parameter already has a description. The description adds a slight hint that exclusion modifications can be done simultaneously, but it does not explain the precedence of setExclusions over add/remove (which is in the schema). Since the schema already documents the parameters, the description adds minimal additional meaning, matching the baseline of 3.

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 a specific action: cloning an existing policy to create a new one, and adds that it can also add/remove exclusions. This distinguishes it from siblings like update_exclusions or delete_policy, which operate on existing policies. The verb+resource combination is precise and unambiguous.

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

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

The description implies the tool is for creating a new policy based on an existing one, but it does not explicitly state when to use it over alternatives like update_exclusions, nor does it mention any exclusions or conditions for use. The context is clear enough to infer, but explicit guidance is absent.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose the core destructive action and the useful failure mode that eBay rejects deletion when listings are linked. Still, for a delete tool it does not state permanence/reversibility, permission requirements, or the dryRun default behavior, leaving meaningful gaps.

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 no filler. The core action is front-loaded and the critical eBay rejection caveat is included efficiently in parentheses.

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 two-parameter tool with full schema coverage, the description is nearly complete. It clearly states what the tool does and a major operational constraint. It could be improved by explicitly pointing to bulk_delete_policies for multi-policy deletion and by noting the destructive permanence, but these are minor for this complexity level.

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 policyId and dryRun already fully documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the 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 the specific verb '削除' (delete) and names the exact resource, '単体フルフィルメントポリシー' (single fulfillment policy). The '単体' qualifier clearly distinguishes it from the sibling bulk_delete_policies, and the parenthetical about eBay rejecting deletion when listings are linked adds precise 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 '単体' qualifier signals this is for deleting one policy at a time, which implies bulk operations belong to bulk_delete_policies. It also states the key precondition/failure condition: deletion is rejected if there are linked listings. However, it does not explicitly name an alternative tool or give a direct 'use this when...' statement.

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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It states the action but does not disclose whether the operation is read-only, whether it overwrites an existing file, or any permission or side-effect requirements. For an export tool, this is a notable gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core action and output. There is no redundant or filler content, making it highly concise and well-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?

For a simple export tool with one parameter and no output schema, the description covers the essential what and output format. However, it lacks any mention of file handling behavior (e.g., overwrite vs. create new) or prerequisites (e.g., existing policies). Given the absence of annotations, this is a moderate gap but not critical for a straightforward export action.

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 parameter outputPath is already documented in the schema. The description does not add any additional meaning about the parameter beyond what the schema provides. Per the baseline, a score of 3 is appropriate when the schema fully covers parameter semantics.

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 'export', the resource 'all policies' exclusion settings', and the output format 'Excel pivot'. This is specific and distinguishes it from siblings like get_policy_exclusions (which likely returns data) and import_excel (which imports). The purpose is unambiguous.

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

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

No guidance is provided on when to use this tool versus alternatives. It does not mention that it is the export counterpart to import_excel, nor does it clarify when one would choose this over get_policy_exclusions or bulk_update_exclusions. The agent is left to infer usage from the name and description.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. '取得' conveys a read operation and '人間が読める形' discloses the output style, but it does not explicitly state read-only/side-effect-free behavior, error conditions, or what happens when the policy has no exclusions.

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 one short sentence with no filler. It leads with the resource/action and appends the useful output-format qualifier, so 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 single-parameter read tool with no output schema, the description is mostly complete: it names the target, the input, and the output form. It could add a note about return structure or empty results, but the low complexity and fully documented parameter keep the gap small.

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% and the only parameter, policyId, is already described as the fulfillment policy ID. The description adds little semantic value beyond tying it to a 'specific policy,' so the baseline 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 states a specific action ('取得' retrieve) on a specific resource ('特定ポリシーの除外設定' exclusion settings for a specific policy). It also notes the output is human-readable, which clearly distinguishes it from sibling tools like update_exclusions or delete_policy that perform 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 phrase '特定ポリシーの' implies this is for retrieving exclusions for a single policy identified by policyId. However, it does not explicitly state when to choose this over alternatives such as bulk_update_exclusions or list_policies, and it gives no exclusions or alternative names.

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?

No annotations are present, so the description must disclose behavioral traits. It states the action ('反映') but does not mention the dryRun parameter, which is critical for preview vs. actual application, nor any side effects like overwriting existing exclusions. This is a significant gap for a mutation 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?

The description is a single, concise sentence that immediately states the core purpose. There is zero filler or 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 description is minimal for a mutation tool. It omits the existence and behavior of the dryRun parameter, which is essential for safe usage. It also does not explain the expected Excel format or any prerequisites. Even with schema coverage, the main description should mention the preview option to prevent accidental changes.

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% for both parameters (filePath and dryRun), so the schema already documents them. The tool description adds no extra meaning beyond the schema, meeting the baseline for high 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 the action ('反映' = reflect/apply) and the resource (exclusion settings from pivot-format Excel to eBay). It is specific enough to distinguish from siblings like export_all_excel (export) and update_exclusions (direct update), though it does not explicitly name an alternative.

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 guidance is given on when to use this tool versus alternatives such as update_exclusions or bulk_update_exclusions. The use case is implied by the name and description but no explicit when-to-use or when-not-to-use 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?

With no annotations, the description carries the burden of indicating a read-only action, and '取得' does convey retrieval rather than mutation. However, it does not disclose pagination, output shape, permissions, or the impact of the optional marketplaceId, leaving some behavioral details implicit.

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 front-loaded sentence with no wasted words or redundant information. It immediately identifies the action and resource, making it easy to scan.

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 optional parameter and no output schema, the description is adequate in conveying the basic purpose. It is less complete because there are no usage exclusions, no annotations, and no mention of default marketplace behavior or return format beyond the implied list.

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% and the single parameter marketplaceId is documented with its default, so the schema already explains the parameter. The tool description adds no parameter-specific meaning, which matches 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 the verb '取得' (retrieve) and the resource '全フルフィルメントポリシー一覧' (all fulfillment policies list), so an agent can tell what it does. It does not explicitly name a sibling alternative, but the scope 'all' helps distinguish it from single-policy or shipping-service 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?

No guidance is given about when to prefer this tool over alternatives such as delete_policy, get_policy_exclusions, or list_shipping_services. The description implies it is for retrieving all fulfillment policies but never states when not to use it or which sibling covers other needs.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention that this is a read-only operation (though implied), nor does it disclose any rate limits, authentication requirements, response format, or pagination behavior. For a simple list tool, this is a minimal gap, but it is still lacking.

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, efficient sentence in Japanese that conveys the purpose without extra words. It is appropriately front-loaded and not verbose. It earns a high score for conciseness, though it sacrifices some explanatory depth.

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 three optional parameters and no output schema. The description covers the core purpose but does not explain the return format, pagination, or any edge cases. Given that the schema already documents parameters, this is adequate but not rich. A slightly more complete description would mention the response structure or the scope of the list.

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 (filter, policyId, marketplaceId) having its own description. The tool description adds no additional parameter semantics beyond what the schema already provides. The baseline of 3 is appropriate when the schema fully documents parameters.

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 a clear verb and resource: 'Get the list of shipping services for policies'. It is distinct from siblings like list_policies (which lists policies themselves) and add_shipping_service (which adds). However, it does not explicitly differentiate from any sibling by name, so it is clear but not maximally specific.

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 guidance is given on when to use this tool versus alternatives. There is no mention of conditions, exclusions, or preferred scenarios. The description only states what it does, leaving the agent to infer that it is a read-only listing operation.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not reveal that dryRun defaults to true (preview mode), does not state whether removal is destructive or reversible, and does not explain how the 'INTERNATIONAL' scope interacts with the filter or policyId parameters. For a deletion tool this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is structurally simple, but this brevity is under-specification rather than efficient conciseness. No structured guidance (scope, safety, alternatives) is front-loaded; the sentence earns its place but says too little.

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 deletion tool with 4 parameters, no annotations, and no output schema, the description is incomplete. It omits dryRun semantics (preview vs apply), the meaning of INTERNATIONAL, the relationship between filter and policyId, and what happens after the service is 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 description coverage is 100%, so the baseline is 3; the schema already documents all four parameters. The description adds no meaning beyond the schema and, if anything, the 'INTERNATIONAL' reference could confuse an agent about which parameter controls scope, since no parameter description mentions INTERNATIONAL.

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 a verb (削除/delete) and a resource (shippingService), so the basic purpose is identifiable. However, 'INTERNATIONAL' is an unexplained scope term that doesn't map clearly to any parameter (filter, policyId, service) and does nothing to distinguish this tool from siblings like add_shipping_service or list_shipping_services. The purpose is only partially clear.

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 guidance is given on when to use this tool versus the alternatives. There is no mention of when to prefer remove_shipping_service over delete_policy, bulk_delete_policies, or add_shipping_service, and no prerequisites or exclusions are stated.

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?

With no annotations, the description must disclose behavior, but it only states that the order is changed. It does not mention that dryRun previews changes, that the operation is a mutation, whether it is reversible, or any side effects. The schema's dryRun field is not referenced in the description.

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 no redundancy, which is efficient. However, it is under-specified, lacking essential context like what INTERNATIONAL refers to. It is concise but not sufficiently informative.

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 4 parameters and no output schema, the description is far too sparse. It does not explain the meaning of INTERNATIONAL, the purpose of dryRun, filter, or policyId, or how to construct a correct call. An agent would have to rely entirely on the schema, which may not provide domain 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 description coverage is 100%, so the schema fully documents each parameter. The description adds no extra meaning or relationships between parameters (e.g., how filter or policyId interact with service). It does not compensate for potential ambiguities 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 states the action (change the order of shippingServices) and a target (INTERNATIONAL), but 'INTERNATIONAL' is ambiguous—it could refer to a policy type or a specific policy. It does not differentiate from sibling tools like add_shipping_service or remove_shipping_service, and the parenthetical 'move specified service to front' adds detail but is not fully integrated.

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 guidance on when to use this tool versus alternatives. There is no mention of prerequisites, conditions, or exclusions. An agent would not know if this is for a specific policy scope or how it compares to other shipping-service 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?

With no annotations, the description carries the full behavioral burden, but it only says 'update' and gives no detail. It does not disclose that dryRun defaults to true (preview only), that setExclusions replaces the list, or how add/remove interact.

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?

It is a single short sentence with no filler, and the scope is front-loaded. It is economical, though its terseness limits the amount of guidance it provides.

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 schema is rich enough to allow a correct call, but the description lacks any statement about side effects, interaction among the three exclusion arrays, or return behavior. For a mutation tool with no annotations and no output schema, it is minimally adequate rather than 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 the baseline of 3 applies. The description itself adds no parameter meaning, but the schema already documents dryRun, policyId, addExclusions, setExclusions, and removeExclusions with examples.

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 a clear action and resource: '特定ポリシーの除外設定を更新' (update exclusion settings for a specific policy). The modifier '特定' (specific) helps distinguish it from sibling bulk_update_exclusions, which handles multiple policies.

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 establishes that this tool targets a single, specified policy, but it never explicitly says when to prefer it over bulk_update_exclusions or suggests reading get_policy_exclusions first. The usage context is implied rather than stated.

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