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

Discloses idempotent behavior (no duplicate errors) and that multiple tags can be assigned. Without annotations, this covers key behavioral traits, though permission or error cases are not mentioned.

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 with zero waste. Front-loaded with the primary action, followed by important behavioral notes and usage guidance.

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?

Adequately covers the tool's purpose, idempotency, and when to use alternatives. No output schema needed. Missing error scenarios but still fairly complete for a simple mutation.

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 covers parameters fully (100%). Description adds idempotent context and 'one or more' nuance, but adds limited new semantic value beyond what 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 clearly states the action: assigning one or more tags to a single friend. It distinguishes from the sibling tool 'bulk_add_tag' by specifying single vs multiple targets.

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 using 'bulk_add_tag' for multiple targets, providing clear when-to-use guidance. No exclusions or prerequisites are mentioned, 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?

Discloses idempotence (should be tol) as key behavioral trait. No annotations exist, so description fully covers this. No mention of destructive effects, but the operation is additive and safe.

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 efficient sentences. First sentence defines purpose and idempotence, second provides usage guidance. 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?

For a simple batch operation with 2 params and no output schema, the description covers purpose, behavior, and usage guidance comprehensively. No gaps given context signals.

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 3. Description does not add extra semantics beyond the schema descriptions. The parameter names and types are self-explanatory.

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 ('一括付与する' = batch assign) and resource (one tag to multiple friends). It distinguishes from the sibling tool 'add_tag_to_friend' by noting that tool is simpler for single targets.

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 this tool (batch assignment) and when to use the alternative (single friend). Also explains idempotent behavior, so no error for already-assigned friends.

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, description covers idempotency and error handling (ignores non-tagged friends). Lacks info on invalid tag_id or return value, but sufficient for a simple removal.

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 in one paragraph, front-loaded with main purpose, then details and sibling comparison. 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?

Tools has no output schema and simple parameters. Description covers core behavior, idempotency, and alternative. Missing return value info but 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 already describes both parameters fully (100% coverage). Description adds no new parameter-specific info; 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?

Description clearly states it removes one tag from multiple friends (specific verb+resource) and distinguishes from sibling 'remove_tag_from_friend' by noting the bulk behavior.

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 when to use this tool (bulk case) and when to prefer the simpler remove_tag_from_friend for single target, plus notes idempotent nature.

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 provided, the description carries full burden. It accurately describes the tool's creation behavior and folder handling, but lacks details on permissions, idempotency, error conditions, or side effects. For a creation tool this is minimal but not insufficient.

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 redundancy. The main purpose is front-loaded, followed by crucial usage caveats. Every sentence adds value without fluff.

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 (3 parameters, no output schema), the description covers the key aspects: what it creates, what it doesn't do (value setting), and folder behavior. It could mention error handling (e.g., duplicate names) but remains adequate for typical use.

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%, providing baseline of 3. The description adds value by explaining the purpose of the definition (values differ per friend) and the default behavior for folder_id (unclassified when omitted), going 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 tool creates a custom attribute definition for friends, distinguishing it from value-setting tools. It specifies the resource (friend info definition) and action (create), and differentiates from sibling tools by noting that value setting is not implemented in this connector.

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 (to create a definition) and when not (value setting is separate and not available). It also explains the behavior of the folder_id parameter when omitted. This provides clear guidance on usage 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?

No annotations are provided, so the description carries full burden. It discloses that only creation is allowed and no update/delete, which is important behavioral info. It does not mention permissions or side effects, but for a simple folder creation, this is adequate.

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, no wasted words. First sentence states action and purpose, second sentence adds a crucial constraint. Front-loaded with key info.

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 creation tool with one required parameter and no output schema, the description is fairly complete. It explains purpose, the resource type, and the only limitation. Could be improved by noting that folders are used to organize custom attributes, but it's already implied.

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 one parameter 'name'. The description adds context by explaining what the folder is for (organizing friend info), which gives semantic meaning beyond the schema's 'folder name'. This compensates for the lack of param 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 it creates a folder for organizing friend information, explicitly distinguishing it from sibling tools like create_tag_folder by specifying 'friend info'. The verb 'create' and resource 'folder' are 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?

The description notes that only creation is possible and no delete/update APIs exist, which helps the agent set expectations. However, it does not explicitly compare to alternatives like create_tag_folder, though the context implies the distinction.

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, so description carries full burden. Discloses key behaviors: tag creation, optional folder, no delete API. Could add detail on name uniqueness or permissions, but sufficient for basic transparency.

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 with no redundancy. Each sentence adds distinct information: action, folder behavior, delete limitation.

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?

Missing output schema description—no mention of return value (e.g., created tag ID). Also lacks name format constraints or uniqueness. Adequate for basic use but incomplete for full context given its criticality as a creation 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 adds value by stating folder_id default behavior (unclassified folder) not in schema. Enhances understanding beyond parameter 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?

Description clearly states '新しいタグを作成する' (create a new tag), with specific verb and resource. It also clarifies folder behavior and absence of delete API, distinguishing it from siblings like add_tag_to_friend and create_tag_folder.

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 guidance on folder_id default, but lacks explicit when-to-use vs alternatives. Does not mention prerequisites or scenarios for this tool versus create_tag_folder or bulk_add_tag.

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 full responsibility for behavioral disclosure. It discloses a key behavioral trait: no delete/update API exists, which sets user expectations. However, it does not mention other behaviors like whether creation is idempotent, what happens on duplicate names, or required 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?

The description is two sentences: the first clearly states the purpose, the second adds important behavioral context. It is concise, front-loaded, and contains 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 simplicity of the tool (one parameter, no output schema), the description covers the core purpose and a notable limitation. However, it lacks details about return value (e.g., created folder ID), error cases, and prerequisites. It is adequate but not fully 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?

There is only one parameter (name) with full schema description coverage (100%). The description does not add any additional meaning beyond the schema's 'folder name'. According to the baseline rule for high coverage, a 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 verb 'create' and the resource 'tag folder'. It distinguishes from siblings like create_tag (creates a tag, not a folder) and list_tag_folders (lists, not creates). 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?

The description does not explicitly state when to use this tool versus alternatives. While it implies that it is for creating a folder for tags, it does not provide guidance on prerequisites or situations where other tools like create_tag might be more appropriate. The note about no delete/update API is helpful but not strictly a usage guideline.

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 provided, the description fully carries the burden of behavioral disclosure. It transparently explains ordering, filtering, pagination behavior, and the maximum limit. No contradictions or omissions 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 a concise paragraph that front-loads the purpose and then adds essential details. Each sentence adds value, and there is no redundancy. It is appropriately sized for the tool's complexity.

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 parameters, no required fields, and no output schema, the description covers searching, filtering, sorting, and pagination adequately. It explains how to retrieve subsequent pages and notes the limitation. Missing aspects like error handling are minor for this type of 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%, so the baseline is 3. The description adds some extra context beyond the schema (e.g., default max 1000 items, pagination limitation), but the parameter descriptions in the schema are already quite detailed. The contribution is marginal.

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 (search and retrieve) and the resource (LINE message history with friends). It distinguishes itself from sibling tools, which are about tags and friend management, not message history.

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 detailed usage guidance: default sort order, filtering by friend_id and date range, max items per request, and pagination with cursor (including the limitation of no backward pagination). While it does not explicitly state when not to use this tool, the context is clear given the sibling tools available.

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 discloses key behaviors: no pagination (all results at once) and null id meaning uncategorized folders. This adds value beyond the empty schema.

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 behavioral details. 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 no output schema, the description explains the id field meaning and pagination but does not fully describe the structure of returned folder objects (e.g., name field). Could be more 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?

There are no parameters, so baseline is 4. The description adds context about output and behavior, but no parameter-specific details are needed.

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 'get list' and resource 'common info folders', and references another tool for definition. It distinguishes from sibling tools like list_common_infos which list actual info items.

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?

Usage is implied by mentioning no pagination and referencing list_common_infos for context, but no explicit when-to-use or alternative tools are 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?

No annotations, but description explains it's a read operation, folder_id behavior (null vs omitted), and that elements are used via shortcodes. Lacks explicit safety note but is transparent enough.

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?

Concise, front-loaded with purpose, no redundant sentences. Efficiently covers key points.

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 purpose, distinction, filtering, and usage. Could mention return format (likely array with pagination) but still very complete given no output schema.

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% coverage, but description adds value by explaining folder_id's special behavior (null=unclassified, omitted=all) and context about list 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?

Description clearly states it lists common infos (account-level fixed values), defines them, and distinguishes from friend infos. Sibling tools are about tags, friends, etc., so no ambiguity.

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?

Describes when to use (account-level static data), how it differs from friend infos, and folder filtering. No explicit 'when not to use' or alternatives, 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?

With no annotations, the description carries full burden. It discloses that the tool is read-only ('does not perform writing') and explains pagination behavior with limit and cursor. It does not cover permission or performance details.

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, with four short sentences covering purpose, use case, pagination, and read-only nature. 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 no output schema and no annotations, the description covers key aspects: expanded return, use case, pagination, and read-only. It could briefly mention filtering alternatives (e.g., list_friends_by_tag) but remains 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%, so baseline is 3. The description adds value by explaining limit defaults and max, and cursor usage with previous response's next_cursor, going 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 identifies the tool as retrieving a list of friends with expanded tags, custom attributes, and response marks. It distinguishes from siblings like list_friends_by_tag which filters by tag, making the purpose unique.

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 a use case: checking delivery targets and inventorying customer attributes. It does not explicitly state when not to use it, but the context of sibling tools implies 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?

No annotations provided, so the description must convey behavioral traits. It discloses cursor-based pagination and how to continue fetching. It implies a read-only operation via the verb 'get'.

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 use cases and pagination. Every 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?

For a list tool with cursor pagination and no output schema, the description covers the essential aspects: purpose, pagination mechanism. It does not detail the return format, but the overall completeness is 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%, so baseline is 3. The description adds pagination context for the cursor parameter but does not significantly augment the schema's parameter 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 tool retrieves a list of friends with a specific tag. It provides use cases like batch sending and checking segment count, and distinguishes from siblings like list_friends (unfiltered).

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 mentions two scenarios where this tool is useful, but does not explicitly mention alternatives or when not to use it. However, the context is clear enough.

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. It discloses one behavioral trait (no pagination, returns all at once), which is valuable. However, it does not mention other traits like read-only status, authorization needs, or rate limits, leaving gaps in transparency.

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 short sentences that convey the purpose and a key behavioral detail. Every word serves a purpose, and there is no redundancy or irrelevant 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 that the tool has no parameters, no output schema, and no annotations, the description is largely complete for a simple list-all tool. It could optionally mention the output format (e.g., list of folder names/IDs), but this is not strictly necessary for an agent to understand the tool's function.

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 has no parameters, so the baseline score is 4 per the rubric. The description does not need to add parameter meaning, and it does not attempt to describe any parameters, 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 action (list/get) and resource (tag folders), and distinguishes from siblings like list_tags and list_common_info_folders by specifying the resource type. It also adds a behavioral detail (no pagination, returns all at once), which is specific and useful.

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 the tool is for obtaining all tag folders without pagination, but it does not provide explicit guidance on when to use it versus alternatives, nor does it mention exclusions or prerequisites. Given the simplicity of the tool, the lack of usage sentences is acceptable but not exemplary.

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 must carry the full burden. It discloses the maximum limit (1000) and default (50), which is useful. However, it does not state that the operation is read-only or safe, nor does it mention any ordering, filtering, or pagination behavior beyond the limit parameter.

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: first states purpose, second gives common use, third provides limit info. No wasted words, well-structured for quick parsing.

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 fully explain the return format (only that fields include ID, name, folder). It also lacks details on pagination control (e.g., how to get next page) beyond the limit parameter. This may leave the agent unsure about handling large result sets.

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 description coverage, the baseline is 3. The description restates the limit parameter's max and default, adding no new information beyond what the schema already provides. It does not explain any other parameters or behavior modifiers.

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 tool retrieves a list of registered tags with ID, name, and folder. It also identifies a specific use case (checking tag IDs before assign/remove), which distinguishes it from sibling tools like list_friends or list_tag_folders.

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 the tool ('often used to check tag IDs before assigning to or removing from friends'), providing clear context. However, it does not mention when not to use it or compare with alternatives like list_friends_by_tag.

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 fully discloses behavior: it returns all marks with ID and name, and states there is no pagination. This covers the essential behavioral traits for a read-only list.

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, each sentence adds value: first states purpose and return format, second states usage and pagination 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?

For a zero-parameter tool without output schema, the description explains what is returned (ID and name), how it is used (for set_response_mark), and that it returns all results. No additional context needed.

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 exist, so the description doesn't need to add meaning; baseline 4 applies as schema coverage is 100%.

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 defines the tool as retrieving a list of taiou marks with ID and name, and distinguishes itself by mentioning its purpose to find taiou_mark_id for set_response_mark.

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 explicitly states the tool is used to check taiou_mark_id for set_response_mark, providing clear usage context. It does not list alternatives or when not to use, but for a straightforward list tool this is adequate.

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 provided, the description carries full burden. It discloses idempotent behavior and the inability to delete tags. However, it does not explicitly state that this is a mutation operation or describe side effects. Overall, it provides solid 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?

The description is three concise sentences, each serving a clear purpose: action, idempotency/alternative, and limitation. No redundant information; it is well-structured and 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?

Given the tool's simplicity (2 parameters, no output schema, no annotations), the description covers all necessary aspects: purpose, behavior, usage context, and limitations. It is fully adequate 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?

The input schema covers both parameters with descriptions (100% coverage). The description adds value by explaining that tag_ids can include unassigned IDs without error (idempotency), which is beyond the schema. This enhances the semantic 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 explicitly states 'remove one or more tags from one friend at once' (友だち1人からタグを1件以上まとめて解除する). It clearly identifies the verb (remove), resource (friend and tags), and scope (single friend, multiple tags), distinguishing it from siblings like bulk_remove_tag.

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 explains idempotency (including unassigned tag IDs is ignored without error) and advises using bulk_remove_tag for multiple friends. It also notes that the tool cannot delete tags themselves, providing clear when-to-use and when-not-to-use 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?

No annotations provided, so description carries full burden. Discloses overwrite behavior but misses permissions, error handling, and return value. Adequate for a simple mutation but could be more comprehensive.

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, no filler, front-loaded with key information. 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 the tool's simplicity (2 required params, no output schema, no enums), it covers the core behavior: setting, overwriting, and ID source. Minor gap: no error case mention.

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 already documents both parameters. Description reinforces that taiou_mark_id comes from list_taiou_marks, adding context 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?

Clearly states setting one response mark for one friend, describes the mark as a label for response status, and notes that existing marks are overwritten. Differentiates from sibling tools by mentioning list_taiou_marks for ID 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?

Explains overwrite behavior and suggests checking list_taiou_marks for IDs. Does not explicitly state when to use versus alternative tools like add_tag_to_friend, but the distinct purpose is implied.

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. It reveals that updates propagate to templates and messages using the shortcode, and that create/delete are unavailable. This provides good transparency for a mutation tool, though it could mention any reversal constraints.

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 primary action, and adds necessary details about side effects and limitations without any fluff. 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?

Despite no output schema, the description fully explains the tool's purpose, impact (value reflects in templates/messages), and constraints (no create/delete). With 2 parameters and complete schema coverage, this is sufficient for an AI agent to use correctly.

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 descriptions for both parameters ('共通情報ID' and '新しい値'). The description adds no extra meaning beyond the schema, so the 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 verb '更新する' (update) and the resource '共通情報' (common info), distinguishing it from the sibling 'list_common_infos' by referencing it for viewing. It specifies that it updates one item's value, providing a clear and unique purpose.

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 explains when to use this tool (for updating a common info) and explicitly states that creation and deletion APIs are not provided, guiding against misuse. It also describes the effect on templates and messages, giving context for impact, though it does not directly compare with other tools like 'add_tag_to_friend'.

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 burden. It openly discloses partial update behavior (omitted fields unchanged) and the inability to delete tags. This provides adequate behavioral clarity for a simple update operation, though it omits auth and rate limits.

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 core action, no 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 simple tool with 3 parameters (1 required) and no output schema, the description covers the update behavior and a key limitation (no delete). It is complete for safe 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 parameters are documented. The description adds critical meaning: omitted parameters are not changed. This goes beyond the schema's 'optional' labels, clarifying the update 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 ('部分更新する' = partially update), resource ('既存タグ'), and scope (name and folder_id). It distinguishes from sibling tools that create or delete tags.

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?

While it mentions that deletion is not possible (a limitation), it does not provide explicit guidance on when to use this tool versus alternatives like create_tag or other update tools. The usage context is implied but not fully elaborated.

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