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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not whether the operation is idempotent, whether it mutates state, what happens if the resource is already favorited, or what authentication/errors to expect. For a mutation-style tool this is a complete 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?

Four words is not conciseness but under-specification — the phrase is front-loaded yet conveys almost nothing beyond the tool name. Sibling to the 'Process'-style tautology examples, it wastes no space but also earns none.

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 one-parameter tool this description is still inadequate: with no annotations and no output schema, the agent gets no confirmation of mutation semantics, idempotency, or failure behavior, all of which the description should have supplied.

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 there is a single parameter, so the schema already documents resourceId fully. The description adds no additional meaning about the ID's format, scope, or constraints, which is the expected baseline 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 phrase '즐겨찾기 표시' merely restates the tool name 'dms_favorite'; it is ambiguous between 'mark this resource as a favorite' and 'show favorites'. It does not distinguish the action from siblings like dms_list or dms_unfavorite, so an agent cannot confidently tell what the call does.

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?

There is no statement of when to use this tool instead of dms_unfavorite, dms_list, or search_files_resources. The only inference an agent can make is from the name's implied opposite (dms_unfavorite), which is not spelled out in the 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 full behavioral burden, yet it says nothing explicit about read-only semantics, pagination (limit/offset), permission requirements, or result ordering. For a 5-parameter listing tool with no output schema, 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?

A single front-loaded sentence with zero filler. It is efficient, though its brevity is partly a symptom of under-specification rather than disciplined conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters, 40% schema coverage, no annotations, and no output schema, the definition is too thin to fully inform correct invocation. Pagination and sorting semantics in particular are left entirely to the 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 description coverage is only 40%: sort and resourceId are documented, but limit, offset, and order are not. The description adds no parameter-level meaning at all, so it fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (조회/list) and resource (파일/폴더 within a 폴더), so the operation is unambiguous. However, it does not differentiate itself from siblings such as search_files_resources and search_folders_resources, which plausibly retrieve overlapping content.

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 gives no when-to-use guidance, no prerequisites, and does not mention any alternative such as search_files_resources or dms_root. An agent must guess whether this or a search tool is appropriate for a given listing task.

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. '조회' implies a read, but nothing is said about permission requirements, behavior for a nonexistent/inaccessible resourceId, or what properties are returned. For a metadata tool with zero annotation coverage this is a substantial 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?

A single front-loaded phrase with no filler or repetition. It is efficient, though arguably terse to the point of under-specification, which is penalized elsewhere rather than here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should at least hint at the returned property set and error behavior; it does neither. It is minimally adequate for a one-parameter lookup whose purpose is unambiguous, but an agent still lacks return-shape 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% and the single resourceId parameter is already documented in the schema ('조회할 파일/폴더의 ID'). The description adds no format, scope, or sourcing detail beyond that, 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 Korean phrase '개별 파일/폴더 속성 조회' gives a specific verb (retrieve/inspect) and resource (properties of an individual file/folder). It contrasts implicitly with list-style siblings such as dms_list by emphasizing '개별' (individual), but it never names an alternative tool explicitly.

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 only implied: '개별' signals single-item metadata lookup as opposed to listing, but there is no explicit when-to-use, when-not, or named alternative among the many siblings (dms_list, search_files_resources, dms_root). The agent must infer the boundary itself.

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 bears the full disclosure burden, yet it only says the operation lists items. It does not state that this is a safe read-only operation, whether results are paginated, ordering defaults, or what happens with empty roots.

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 front-loaded phrase with zero padding, appropriate for a simple list tool. It is efficient, though the brevity edges toward under-specification rather than exemplifying crisp completeness.

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 four parameters, no output schema, and no annotations, the description is too thin: it omits read-only nature, pagination behavior, default sort/order, and how it relates to sibling listing tools. Something more is needed to call this correctly and confidently.

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% (sort, limit, order, offset each documented in the schema, with order having an enum), so the schema carries the parameter meaning. The description adds nothing beyond that, which is the baseline 3 case.

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 phrase '루트 파일/폴더 목록 조회' names a specific verb (조회/list) and resource (root files/folders), so the basic purpose is legible. However, it gives no differentiation from close siblings like dms_list or dms_resourceId, leaving the agent to guess why a root-scoped listing exists separately.

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

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

There is no when-to-use guidance, no mention of alternatives such as dms_list, and no prerequisites or scope constraints stated. The agent must infer from the name alone that this is the root-level variant.

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 behavioral burden. The verb 조회 implies a read-only lookup, but nothing states permission requirements, whether the result is cached, or what scope of files is returned. With 0 parameters the risk profile is low, but the disclosure is still largely absent.

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 phrase with no padding and the purpose is front-loaded. But it is under-specified rather than efficient — the brevity comes at the cost of any operational detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description is the only source of context, and it does not explain which file's properties are returned, how the target file is determined with zero parameters, or how the result relates to sibling listing tools. Inadequate for the surrounding toolset.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the schema baseline of 4 applies. There is nothing for the description to clarify beyond what an empty parameter object already communicates.

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 phrase '내 파일 속성 조회' states a verb (조회/view) and resource (파일 속성/file properties), which is more than a tautology. However, it is ambiguous about scope — which file, whose files, and what 'properties' means — and it does nothing to separate this tool from siblings like dms_root, dms_list, or dms_resourceId.

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?

There is no guidance on when to use this tool rather than dms_root, dms_list, or dms_resourceId, all of which plausibly relate to file structure. No prerequisites, no exclusions, no alternative named.

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 behavioral burden. It says nothing about safety, pagination, permissions, or read-only nature. For a list operation, that's 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 extremely concise—a single three-word phrase—but it is under-specified rather than wasteful. It front-loads the core purpose, though it lacks any supporting detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% parameter coverage, the description is far too terse to be adequate. An agent cannot confidently invoke this tool without additional 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 0% and the description provides zero information about the four parameters (sort, limit, order, offset). The agent has no idea what these parameters mean or how to use 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 '휴지통 목록 조회' translates to 'Retrieve trash list,' which states a verb (retrieve) and resource (trash list). However, it doesn't distinguish this tool from siblings like dms_list or dms_trash_routine, and provides no additional scope or context.

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?

There is no guidance on when to use this tool versus alternatives such as dms_list or files_trash_clean. The description is purely a label, leaving the agent to infer usage from the name alone.

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 behavioral burden. It does not disclose whether this is a persistent account-wide setting, what permissions are required, whether the change applies retroactively to already-trashed items, or what the response is. Only the mutation intent is implied.

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 front-loaded phrase with zero waste. It is a complete verb+object statement rather than a tautology, though the extreme brevity leaves it close to under-specified.

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 one-parameter settings tool with full schema coverage and no output schema, the description is minimally sufficient. It is missing any indication of scope (account vs. workspace), permission requirements, and how it relates to the other trash tools.

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 already documents its allowed values (0, 5, 15, 30, 50). The description adds no meaning beyond the schema — it merely restates the parameter's concept — so the baseline 3 for high coverage 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?

States a specific verb+resource in Korean: setting the trash auto-delete cycle (휴지통 자동 삭제 주기 설정). An agent can tell this configures a retention interval rather than listing, restoring, or emptying trash. It does not, however, differentiate itself from the other trash-related siblings (dms_trash_list, files_trash_clean, files_trash_restore).

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 when-to-use guidance and no mention of alternatives or prerequisites. The agent must infer from the name alone that this is a settings mutation rather than an operation on trashed files, with several trash-related siblings available that it could confuse this with.

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 behavioral burden, yet it discloses nothing beyond the action verb. It does not state whether removal is reversible, what permission is required, or what happens to the resource, which 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 short phrase with no filler and is inherently front-loaded. However, its brevity reflects under-specification rather than efficient communication, since essential context is absent.

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 mutation tool with no annotations and no output schema, the description is far too thin. It omits reversibility, permissions, and confirmation behavior, leaving the agent with only the bare action and the schema-supplied parameter.

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 single resourceId parameter is fully documented in the schema as the file/folder ID to unfavorite. The description adds no additional meaning, so the baseline of 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"즐겨찾기 해제" (remove favorite) conveys a specific action on the favorite state, so the purpose is discernible. However, it largely restates the tool name dms_unfavorite and does not name the target resource type or differentiate itself from the sibling dms_favorite, leaving the agent to infer the 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?

The description provides no when-to-use guidance, no prerequisites, and no mention of the obvious alternative dms_favorite for the inverse operation. Nothing tells the agent when this is the correct tool versus its sibling.

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

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing beyond the verb. It does not state whether copying is a deep recursive copy, what happens on name collision, required permissions, or side effects on the original. For a mutation tool with zero annotation coverage this is a serious 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?

At a single three-word phrase, the problem is under-specification rather than verbosity. There is nothing wasted, but also nothing that earns its place beyond the tool name, so it cannot score as well-structured 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?

With 4 parameters, no annotations, and no output schema, the description is far too thin to guide correct invocation. The agent has no description-level signal about overwrite semantics, destination defaults, or return behavior.

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 all four parameters (name, parentId, resourceId, isOverwrite) documented in the schema itself. Per the rubric, a high-coverage schema sets the baseline at 3, and the description adds no extra parameter meaning.

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 '파일/폴더 복사' (copy file/folder) gives a specific verb (복사/copy) and resource (파일/폴더), which is slightly more than the bare tool name files_copy. However, it provides no scope, no differentiation from adjacent siblings like files_move, files_rename, or files_upload, so it sits at the minimum-viable level.

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?

There is no guidance on when to use this tool versus alternatives such as files_move or files_upload. No prerequisites, no exclusions, no context — the agent must infer all routing decisions from the tool name alone.

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 behavioral burden — yet it discloses nothing about behavior. It does not state what happens on duplicate names, whether the folder is created at root by default, whether it is reversible (it is a mutation), or any permission requirements.

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 two-word phrase that is under-specified rather than concise. Brevity here reflects missing information, not efficient front-loading.

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?

This is a mutation tool with no annotations, no output schema, and no explanation of return values or effects. An agent cannot determine error behavior, overwrite semantics, or default placement from the description alone.

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%: both parentId ("상위 폴더 ID(생략 시 루트)") and folderName are fully documented in the schema. The description adds no parameter meaning beyond that, 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?

"폴더 생성" (create folder) merely restates the tool name files_create_folder — a tautology with no additional specificity. It does not distinguish this tool from siblings like files_copy, files_move, or files_rename, which is especially relevant given the large set of file-operation siblings.

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

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

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no mention of the parentId/root placement decision. The schema's parentId description hints at root vs. nested placement, but the description conveys nothing.

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 behavioral burden. The verb 'delete' does signal a destructive operation, but the description never states whether deletion is reversible (trash vs permanent), what permissions are required, or how batch failures are handled for a multi-ID delete.

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?

Four characters is not conciseness but under-specification: the description is too small to front-load anything meaningful. Compare with the calibration example where 'Process' scored similarly for being underspecified rather than 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?

For a destructive, unannotated operation that is one of many trash/delete siblings, the definition is missing the essential facts an agent needs before invoking it: permanence, recoverability, and the sibling that reverses it. The simple single-parameter input keeps this from being a 1.

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 there is only one parameter (resourceIds) whose semantics, including comma-or-array handling, are fully documented in the schema. The description adds nothing beyond it, 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?

States a verb+resource ('파일/폴더 삭제' = delete file/folder), which is more than the tool name alone conveys since it clarifies folders are included. However it is essentially a restatement of the name and does nothing to distinguish it from delete-adjacent siblings like files_trash_clean, files_trash_restore, or files_trash_clean_resourceId.

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?

There is no when-to-use guidance at all — no indication of whether this moves items to trash or permanently removes them, and no pointer to files_trash_restore or files_trash_clean as alternatives. With six delete/trash-related siblings, this omission is costly.

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 behavioral burden, yet it says nothing about whether the URL is temporary or permanent, whether it requires authentication, or whether it expires. For a link-generation tool these traits are essential and are entirely absent.

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 front-loaded phrase with zero waste, appropriate for a one-parameter tool. It is arguably too sparse, but nothing in it is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description should at least explain that the return value is a URL and any validity constraints. Those omissions leave the agent unable to reason about the result or about permission requirements.

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?

Only one parameter exists and the schema already documents it at 100% coverage ('다운로드할 파일의 ID'). The description adds no information beyond the schema, 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 ('파일 다운로드 URL 생성' / generate file download URL) states a specific verb and resource, so an agent can tell it is a URL-issuing tool rather than an actual file-transfer tool. It does not contrast itself with the many sibling tools (files_upload, files_copy, files_delete), but the action 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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives such as directly fetching content. The agent is left to infer that this produces a link rather than the file bytes.

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 behavioral burden, yet it discloses nothing: not whether the move is reversible, what permissions are required, how name collisions are handled, or what happens to existing content at the destination.

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 phrase with no waste, but the brevity reflects under-specification rather than discipline — there is nothing front-loaded because there is nothing beyond a restated name.

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 mutation tool with three parameters, no annotations, and no output schema, the description is inadequate: an agent cannot learn from it what a move does to existing resources, whether it is destructive, or how isOverwrite interacts with the operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with Korean descriptions for resourceId, parentId, and isOverwrite, so the schema fully documents the parameters. The description adds no semantics beyond the schema, which is the baseline 3 when structured data does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase '파일/폴더 이동' (move file/folder) states a verb and a resource, and adds that folders are included, which is slightly more than the name files_move. However, it is essentially a restatement of the tool name and offers no differentiation from siblings like files_copy, files_rename, or files_trash_restore.

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?

There is no guidance on when to use this tool versus the many similar siblings (files_copy, files_rename, files_delete). No prerequisites, no mention of scope (same drive vs cross drive), no 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about permissions, overwrite behavior, error cases, or side effects of renaming, which is critical 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 short phrase, which is concise but severely under-specified for a tool with two required parameters. It lacks any structure or supporting detail, making it insufficient rather than appropriately sized.

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, the schema covers parameters well, but with no annotations and no output schema, the description is missing essential behavioral context (e.g., whether the rename is safe, how collisions are handled). It is not complete enough for an agent to call it confidently.

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 explains both parameters in Korean. The description adds no additional semantic meaning beyond the action itself, which is 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 states a clear verb (change name) and resource (file/folder), making the tool's purpose immediately understandable. It does not, however, differentiate from siblings like files_move, which could also alter a resource's name or path, so it falls short of 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?

There is no guidance on when to use this tool versus alternatives. The description gives no context, prerequisites, or exclusions, leaving the agent to infer usage entirely.

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 behavioral burden for a destructive, likely irreversible operation. It conveys only the scope ('entire trash') and says nothing about permanence, confirmation, required permissions, or what happens to restorable items.

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 four-word phrase with no filler and the destructive action front-loaded. It is appropriately minimal for a zero-parameter tool, though brevity borders on under-specification rather than genuine economy.

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 destructive bulk-delete with no annotations, no output schema, and several closely named siblings, the description is too thin. An agent gets the action but not the risk profile, the distinction from files_trash_clean_resourceId, or any confirmation semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate at the parameter level, and schema coverage is reported at 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 phrase '휴지통 전체 삭제' states a concrete verb (delete) and resource (entire trash), and the qualifier 전체 ('entire') implicitly separates it from the sibling files_trash_clean_resourceId, which scopes to a single resource. It never names that sibling explicitly, so differentiation is inferential rather than stated.

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?

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites or alternatives such as files_trash_restore or files_trash_clean_resourceId. The agent must infer that this bulk-empties the trash rather than targeting one item.

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 does disclose the critical trait — the deletion is permanent and therefore irreversible — but says nothing about required permissions, confirmation behavior, or error cases.

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 short line with zero padding, and the destructive nature is front-loaded. Slightly terse even for its size, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, no-output-schema tool the description covers the essentials: what it deletes and that the action is permanent. It omits any routing to alternatives, which matters given the dense trash-related sibling set.

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 there is only one parameter, so the schema already documents resourceId fully. The description adds no syntax or format detail beyond what is in the schema, matching the baseline for a fully documented single parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: deleting a particular file inside the trash, and flags it as permanent. The word '특정' (specific) scopes it against the bulk sibling files_trash_clean, though no sibling is named explicitly.

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 when-to-use or when-not-to-use guidance. An agent must infer from the name and the word '특정' that this targets one resource rather than emptying the trash wholesale; the alternative files_trash_clean and files_trash_restore are never mentioned.

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, and it discloses nothing. It does not say what happens if the resource no longer exists, whether restore can overwrite existing items (despite an isOverwrite parameter), or what permissions are needed for a mutating operation.

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 words are technically concise but this is under-specification rather than efficient communication. Nothing is front-loaded because nothing is said beyond the tool name.

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 mutating tool with no annotations and no output schema, the description is completely inadequate. It leaves the agent without any information about side effects, error conditions, or the overwrite semantics implied by the second parameter.

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 both resourceId and isOverwrite. The description adds no parameter meaning at all, which lands at the baseline of 3 for fully documented schemas.

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 "휴지통 복원" (trash restore) is essentially a Korean restatement of the tool name files_trash_restore. It conveys the general action but adds no distinguishing scope or detail, and does nothing to separate it from siblings like files_trash_clean or dms_trash_list.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives among the many trash-related siblings. The agent must infer everything from the tool name alone.

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 behavioral burden and fails it. It does not disclose whether the returned URL expires, whether calling this alone creates a file record, what permissions are required, or how isOverwrite/resume interact with existing files.

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 single phrase is front-loaded and wastes no words, but it is under-specification rather than genuine conciseness. Nothing is redundant, yet nothing beyond the tool name is conveyed.

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 7-parameter tool with no annotations and no output schema, the description omits critical context: how the generated URL is used, its lifetime, and how resume/offset semantics change the call. The schema covers the field meanings, but the overall workflow context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all seven parameters already carry Korean descriptions of their own (offset, resume, fileName, fileSize, parentId, isOverwrite, modifiedTime). The description adds no parameter meaning beyond the schema, 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 phrase '파일 업로드 URL 생성' names a specific action and resource (generate a file-upload URL), which is clearer than a bare name restatement. However, it gives no hint of scope, required identifiers, or how it differs from siblings like files_download, files_copy, or files_move, so an agent cannot disambiguate from the text alone.

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 when-to-use guidance, no prerequisites, and no mention of alternatives. The description does not say whether this is the mandatory first step before an actual upload, nor when resume/offset mode applies versus a fresh upload.

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 behavioral burden, yet it discloses nothing: no read-only confirmation, no pagination behavior for limit/offset, no result format, no rate limits. Two words cannot cover this for a 6-parameter search tool.

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

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

Two words are not concise, they are under-specified. Brevity only earns credit when the content is complete; here essential information is simply absent rather than efficiently compressed.

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 6 parameters, no output schema, no annotations, and 20 sibling tools including a near-duplicate search_folders_resources, the description is completely inadequate. An agent cannot call this correctly without opening the schema and guessing at pagination semantics.

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 only 33% (type and query are documented in Korean; sort, limit, order, offset are bare). With four undocumented parameters and zero parameter meaning added by the description, the agent must guess the sort/order/limit/offset contract entirely.

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?

"파일 검색" states a verb (검색/search) and a resource (파일/file), so the basic purpose is inferable. However, it gives no scope, no differentiation from the sibling search_folders_resources, and no indication of what kind of files or repositories are searched.

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?

There is no when-to-use guidance, no mention of alternatives such as search_folders_resources, and no prerequisites or exclusions. An agent has no basis for choosing this tool over its near-identical sibling.

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

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing. It does not mention pagination (despite limit/offset params), sorting behaviour, result shape, or any auth/scope requirements.

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?

Six characters contain no wasted words, but this is under-specification rather than conciseness. There is no front-loaded intent statement an agent can act on.

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 five-parameter search tool with a single enum, no output schema, and no annotations needs substantial description to be callable correctly. This provides none of it, so the definition is inadequate for the tool's 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 description coverage is only 20% — just the required 'query' parameter has a description ('검색어'). The other four parameters (sort, limit, order, offset) are undocumented in both schema and description, and the description itself adds zero parameter meaning.

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 '폴더 검색' is a direct restatement of the tool name (search_folders_resources) in Korean — essentially a tautology. It conveys the verb and resource but adds no scope, and it does nothing to distinguish this tool from the sibling search_files_resources.

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?

There is no when-to-use guidance, no conditions, and no mention of the obvious alternative search_files_resources. The agent must infer from the name alone that this searches folders rather than files.

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