stagenth · file-relay

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

With no annotations provided, the description fully covers key behaviors: recursive creation (like mkdir -p) and idempotency. This is sufficient for an agent to understand the tool's safety and side effects.

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

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

Two short sentences, no fluff. Every word adds value. The structure is front-loaded with the core purpose, then a clear behavioral note.

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

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

For a simple tool with one parameter, no output schema, and no annotations, the description is complete. It explains purpose, behavior (recursive and idempotent), and parameter semantics are well-covered by 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?

The input schema has 100% coverage of folder_path, with detailed description already. The description adds no extra meaning beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description clearly states the tool creates a folder, likening it to mkdir -p, and highlights idempotency. This distinguishes it from siblings like delete_folder, move_folder, and list_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 implies when to use (creating folders recursively) and mentions idempotency, but lacks explicit guidance on when not to use or alternative tools. Sibling tools provide context but not directly stated.

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

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

No annotations are provided, so the description carries full burden. It does not disclose whether the tool is destructive, what it returns, or any side effects. The minimal description leaves the agent uninformed about key behavioral traits.

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

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

The description is a single sentence, very concise and to the point. For a simple tool, this is appropriate, though it could be slightly longer to cover missing details. No unnecessary text.

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

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

Given no output schema and no annotations, the description should provide more context about return values, constraints, and usage. It only covers the basic purpose, leaving the agent with insufficient information to fully understand the tool's 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 coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the parameter descriptions already present in the schema. It does not explain how parameters relate or provide examples.

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

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

The description '为文件生成一个分享链接。' clearly states the action ('generate a share link') and the resource ('for a file'). It distinguishes the tool from siblings like 'download_shared_file' and 'import_shared_file', which are about using existing links rather than creating them.

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 guidance on when to use this tool versus alternatives, nor does it mention prerequisites (e.g., file must exist). Sibling tools include sharing-related actions but no comparative context is given.

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

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

No annotations provided, and the description only states 'delete' without disclosing behavioral traits such as permanence, side effects, or permission requirements. The agent gains no insight beyond the name.

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 at one short sentence, but it is not wasteful. It earns its place by stating the core purpose, though more detail could be added without sacrificing 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?

For a deletion tool with no output schema and no annotations, the description fails to cover important context such as success/failure behavior, error handling, or whether deletion is permanent. This leaves the agent underinformed.

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

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

Schema coverage is 100% for the single parameter, and the description does not add meaning beyond the schema's '文件 ID' (File ID). Baseline of 3 is appropriate as the schema already documents the 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?

The description clearly states the verb 'delete' and the resource 'file', distinguishing it from sibling tools like delete_folder. It is concise but lacks additional 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?

No guidance on when to use this tool versus alternatives, prerequisites, or consequences of deletion. The description omits context that would help an agent decide between this and similar tools.

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

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

Describes soft deletion (recycle bin, 30-day recovery), partial failure behavior (one failure doesn't affect others), and per-ID result return. With no annotations, this is 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 concise sentences with clear structure: first states the core action and recovery note; second explains granular behavior.

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

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

Covers all needed aspects: what it does, side effects, error handling, and return data. No output schema needed as description clarifies per-ID results.

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

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

Schema already describes the parameter (file_ids array, max 100, list_files reference). Description adds batch behavior but no new parameter-level detail 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?

Description clearly states tool deletes files in batch, moves to recycle bin, and is recoverable. The verb 'delete' with 'files' and the qualifier 'batch' differentiate from single-delete siblings like delete_file.

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

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

Description implies usage for multiple files via 'batch' and 'one by one' handling, but does not explicitly state when to use this over single-file tools. The sibling names provide 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?

Discloses soft-delete behavior with recycle bin and 30-day recovery window. No annotations provided, so description carries full burden; covers important side effects.

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 main purpose. Every sentence adds value; no redundant information.

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

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

Explains side effects and recovery window. Lacks explicit output format or sync/async behavior, but for a deletion tool this is sufficient 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 descriptions already cover both parameters fully (100% coverage). Description adds general context about soft delete but not specific parameter semantics 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?

Directly states it deletes a folder, similar to rmdir/rm -r. Distinguishes from sibling tools like create_folder, move_folder, etc. by the deletion action.

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 context about recursive flag behavior (folder must be empty or use recursive). Implicitly suggests when to use recursive=true. Could be more explicit about alternatives like delete_file but 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, description fully bears transparency burden. It discloses: batch deletion, individual failure isolation, per-path result return, and soft delete with 30-day web recovery. This is adequate for a mutation tool. Could add permission requirements or reversal details, but given missing annotations, it's still informative.

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

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

Three sentences, front-loaded with purpose, efficient delivery of core behavioral information. No wasted words.

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

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

Given the tool's batch nature and soft-delete behavior, the description covers purpose, failure handling, and recovery. No output schema exists, but mentions return of per-path results. Could elaborate on response shape or error cases, but current level suffices for agent selection.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by explaining batch behavior ('逐个删除, 单个失败不影响其余; 返回每个路径的结果') and the 50-path limit (mentioned in parameter description, not just schema). The recursive parameter is well-described in schema; description provides overall context beyond individual parameter 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?

Clearly states it is a batch delete for folders ('批量删除文件夹'), explicitly identifies as the batch version of 'delete_folder', and describes key behavioral differences (individual failures independent, returns per-path results). This distinguishes it from the single-folder sibling tool and gives specific verb+resource.

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 frames as batch version of delete_folder, hinting when to prefer this tool over the single version. Mentions max 50 paths. However, lacks explicit 'when not to use' or alternative suggestions beyond sibling reference.

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 important behavioral traits: auto-selection of content block types, speed limits per membership tier, and zero side effects on shares. However, it does not explicitly state authentication requirements for the initial call, though that is often assumed.

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

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

The description is well-structured with clear sections and bullet points. It is somewhat verbose but every sentence adds value. It earns its length without being excessively long.

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

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

Given the complexity (3 parameters, no output schema, no annotations), the description covers behavior for different file types, speed limits, side effects, and MCP content type implications. It lacks details on error handling or what happens when both file_id and file_uuid are provided, but overall it is fairly 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?

The description adds meaning to the as_text parameter by explaining its scope (only for text/code files). However, it provides no additional guidance for file_id or file_uuid, which are only minimally described in the schema. Given low schema description coverage (33%), the description partially compensates but not fully.

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 downloads a file and returns it in native MCP content types based on the file category. It is specific about the verb (download) and resource (file), but lacks explicit differentiation from sibling tools like download_shared_file, so it does not achieve a top score.

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

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

The description implies the tool is for downloading personal files (since it mentions no public share record), but does not explicitly state when to use this vs. alternatives like download_shared_file. The guidance is inferred rather than explicit, so a score of 3 is appropriate.

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. It discloses that ownership is not required, no storage quota impact, and download counts toward sharer's traffic. It also explains the as_text parameter yields direct string for text files. However, it does not describe behavior for binary files, error cases (invalid UUID, expired link, wrong password), or 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?

The description is concise, using about 4 lines with clear bullet points. The main purpose is front-loaded, and each sentence adds necessary context 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?

Given no output schema, the description covers return behavior only for text mode (string). It does not explain what is returned for binary files (presumably base64), nor error handling or success confirmation. While it mentions the share link context, it lacks cross-references to related tools like download_file or import_shared_file for comparative completeness.

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

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

All 3 parameters have schema descriptions (100% coverage). The description adds value by clarifying share_uuid format (last segment after /s/), as_text effect (return string without base64 for text), and password as optional. This enriches understanding beyond the schema.

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

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

The description clearly states the tool downloads files via shared link without needing ownership. It gives a specific use case (receiving a /s/<uuid> link) and implicitly distinguishes from siblings like download_file (needs ownership) and import_shared_file (stores to quota).

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: when someone sends a share link for AI to read content. It notes that downloads don't occupy user storage and count toward sharer's traffic, implying it's for temporary access. However, it does not explicitly state when not to use or mention alternatives like import_shared_file for permanent storage.

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 transparently discloses truncation with max_bytes and marking. While it does not explicitly state that the operation is read-only or discuss error handling, the read-only nature is strongly implied and sufficient for this simple tool.

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

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

Two sentences, front-loaded with purpose and examples, second sentence provides alternatives and behavior. No wasted words; every sentence serves a clear purpose.

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

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

Given the tool's simplicity, the description covers the essential aspects: what it does, when to use it, how parameters affect behavior, and key limitations. No output schema is needed as return value is self-explanatory.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining that long text is truncated and marked when max_bytes is reached, which provides behavioral context beyond the schema's default value specification.

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

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

The description clearly states that it returns the content of text-type files (txt/md/csv/json/logs/code), explicitly listing examples. It distinguishes itself from download_file for binary files, making the purpose specific and unambiguous.

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

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

The description explicitly tells when to use this tool (for text files) and when to use an alternative (binary files → download_file). It also mentions truncation behavior for long text, providing clear usage 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?

With no annotations, the description carries the burden of behavioral disclosure. It labels the operation as '查询' (query), implying a read-only action, but does not explicitly state that it has no side effects, nor does it address error behavior or what happens if both parameters are provided.

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 (one sentence) and front-loaded with the core action. Every word serves a purpose, with no redundancy.

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

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

Given no output schema, the description does not explain what '文件详情' (file details) includes. It also omits information about error cases (e.g., file not found) and whether both parameters can be omitted. For a simple tool it is adequate, but it 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?

The schema already describes both parameters. The description adds the key semantic '二选一' (choose one), which is not present in the schema, providing valuable guidance that only one identifier is 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?

Description clearly states it queries single file details and specifies the two identifier options (file_id and file_uuid). This distinguishes it from sibling tools like list_files (for multiple files) or search_files, making its purpose 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?

Description implies usage by stating to provide either file_id or file_uuid, but does not explicitly indicate when to use this tool over siblings like list_files or search_files, nor does it mention any prerequisites or exclusions.

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

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

Discloses truncation behavior via max_depth and max_nodes parameters, and return structure includes a 'truncated' boolean. No annotations provided, so description carries full burden; it does well but could be more explicit about auth or performance.

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, clear sentence followed by a compact return example. Every element serves a purpose with no redundancy.

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

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

Combined with the comprehensive schema, the description covers purpose, usage, return shape, and truncation behavior. Lacking only an explicit explanation of output schema since none is provided, but still sufficient for a tool of this 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 100%, so the schema already documents all parameters thoroughly. The description adds no extra parameter-specific meaning beyond usage context, warranting a baseline score of 3.

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

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

Explicitly states it returns an ASCII tree of folder/file hierarchy. Recommends usage when user asks for directory structure, distinguishing it from sibling list tools like list_files and list_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?

Provides a clear recommendation for when to use (user asks for directory structure). Does not explicitly state when not to use, but context implies alternatives like list_files for non-tree views.

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?

Description implies a read-only operation ('查看'), but with no annotations, it does not explicitly state idempotency, side-effect freedom, or any potential rate limits. For a simple zero-param tool, the minimal description is adequate but lacks important 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?

Single sentence, front-loaded with the verb, zero waste. Perfectly concise for a simple tool.

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

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

Given zero parameters, no output schema, and low complexity, the description is sufficient to convey the tool's purpose. However, adding a brief note about return format or typical usage would enhance completeness.

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

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

No parameters exist, so baseline is 4. Description adds no parameter info, but none is needed. Schema coverage is 100% by default.

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's function: viewing storage quota usage. The Chinese verb '查看' (view) and noun '存储配额使用情况' (storage quota usage) precisely define the action and resource. No sibling tool addresses quota, so it's well-distinguished.

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

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

No guidance on when to use this tool versus alternatives. While no sibling tools cover quota, the description fails to explicitly state that this is the sole tool for quota queries or provide any context about prerequisites or typical scenarios.

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

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

No annotations provided, so description carries full burden. It discloses server-side copy, quota checks, and traffic implications, which are key behavioral traits. However, it omits details on error handling (e.g., wrong password, duplicate file).

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?

Description is extremely concise, with each sentence earning its place. It front-loads the main purpose and adds necessary technical details 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 no output schema, the description explains the outcome (file appears in user's list) and side effects (quota/traffic). However, it does not specify the return value or error cases, leaving minor gaps.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond what the schema already provides for share_uuid and password; it only places them in context.

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 imports a shared file into the current user's file list. It distinguishes from alternatives like download_shared_file by explaining server-side copy versus local download+reupload, providing specific verb and resource.

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?

Implies usage context by describing equivalent behavior and quota effects, but lacks explicit guidance on when to use versus siblings like download_shared_file. Still, 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?

The description discloses recursive default behavior, inclusion of subfolders/has_subfolders, and folder_path to avoid confusion. It does not cover pagination, sorting, or permission requirements, but with no annotations, this level is adequate but not 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?

The description is relatively concise with four sentences, front-loading the main purpose. It could be slightly more structured, but it is efficient and avoids unnecessary verbosity.

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

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

Given the lack of output schema and annotations, the description is incomplete. It does not specify what fields are returned for each file, how pagination works, or edge cases. The addition of subfolder hints is helpful but insufficient for full 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 67%, and the description adds minimal parameter detail beyond schema. It reinforces recursive default but does not explain page, size, search, or category beyond what the schema already provides. The added context about response fields does not directly help parameter usage.

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 lists current user's files with default recursive traversal, and specifies that the return includes subfolder hints. It also distinguishes from get_folder_tree for tree views, but does not differentiate from search_files or list_folders 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?

The description mentions that for directory structure/tree queries, get_folder_tree should be used instead. However, it does not provide guidance on when to use search_files, list_folders, or other sibling tools, leaving usage context incomplete.

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 burden. It discloses error behavior (folder_not_found) and recursive vs non-recursive behavior. Does not mention permission requirements or return format, but sufficient for this 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?

Extremely concise: two sentences covering purpose, error, and sibling. No fluff, front-loaded with main action.

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?

Low complexity tool, no output schema needed. Description covers purpose, parameters, error, and alternative. Complete for the tool's scope.

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

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

Schema coverage is 100%, description adds value by stating error behavior and the 'ls -d' analogy. Additional context on parameter behavior 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?

Description clearly states '列出文件夹' (list folders) and comparisons to 'ls -d' and sibling 'list_files' distinguish it perfectly. Agent knows this tool lists folders only.

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

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

Explicitly mentions alternative 'list_files' for files and error condition for missing path. Could add more context on when not to use, but 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?

With no annotations provided, the description reveals important behavioral traits: the file content (OSS bytes) remains unchanged, only the logical path is altered, and the operation completes in milliseconds. This adds useful transparency beyond the 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?

The description is extremely concise with two short sentences. The main action is stated first, and every word adds value. 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 move operation, the description adequately covers the core behavior, performance characteristic, and the fact that it does not move the underlying data. However, it does not mention error conditions or return values (no output schema), but the tool's simplicity makes this acceptable.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds value by explaining the effect (like `mv`), implying the target path format, and noting that '/' means root. This enhances understanding beyond the schema alone.

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

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

The description clearly states the tool's purpose: moving a file to a specified folder, using an analogy to the Unix `mv` command. It distinguishes from sibling tools like `move_folder` and `rename_folder` by explicitly targeting files.

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 context that the operation is fast and only changes the logical path without moving bytes, which helps understand when to use it. However, it lacks explicit comparisons to alternatives or conditions for use vs. other file manipulation tools.

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

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

With no annotations provided, the description effectively discloses behavior: it recursively updates logical paths of descendants and ensures OSS bytes remain untouched. This adds significant transparency beyond a simple move 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?

The description is concise with two short paragraphs and a code example. No redundant 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?

Despite no output schema, the description covers the effect (recursive path update, no data movement). It is sufficient for an agent to understand the tool's behavior and side effects.

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%, but the description adds value: it provides an example for folder_path, clarifies target_parent_path can be '/' for root, and cross-references rename_folder. This augments 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 '移动整个文件夹' (move entire folder) with a concrete example 'mv /工作/项目A /归档/', providing a specific verb and resource. It distinguishes from sibling tools by mentioning rename_folder for rename scenarios.

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

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

The description provides clear guidance: it gives an example, explains the recursive path update, and explicitly states that for renaming, use rename_folder tool. It does not explicitly mention when not to use, 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?

The description discloses that the tool does not move the parent, which is a behavioral constraint. However, it does not mention side effects, permissions, idempotency, or error behavior, leaving significant gaps given the lack of annotations.

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

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

The description is extremely concise (4 characters) but lacks structure and completeness. While it is front-loaded with the action, it sacrifices clarity and could be expanded to include key details without being verbose.

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 with only 2 parameters and no output schema or annotations, the description is insufficient. It fails to explain return values, success indicators, or error conditions, leaving the agent with incomplete 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?

Both parameters have descriptions in the schema that explain constraints (e.g., no '/' in new_name, uniqueness). The tool description adds no additional parameter semantics, so with 100% schema coverage, a baseline of 3 is appropriate.

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

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

The description clearly states it renames a folder without changing its parent, effectively distinguishing it from move_folder. However, it is very short and in Chinese, which may be a barrier for some users.

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

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

No explicit guidance on when to use this tool versus alternatives like move_folder. The description only implies that it's for renaming while keeping the parent the same, but does not state that explicitly as usage advice.

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. The description adds behavioral context: only scrapes public pages, does not generate content, only format conversion. However, it omits details like auth needs, rate limits, or error handling.

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 two sentences and a bullet point, each sentence adds value without redundancy.

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

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

Given no output schema and no annotations, the description covers purpose, usage restrictions, and parameter semantics via schema. It lacks details on return format but is sufficient for this simple scraping tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema for parameters url, formats, and only_main_content.

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 'scrape' and resource 'public webpage', specifies output as 'clean Markdown for AI reading/summary/extraction', and distinguishes from sibling tools which are file/folder operations.

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

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

The description explicitly restricts usage to public webpages and forbids intranet/reserved addresses, providing clear context. It does not explicitly compare with alternatives, but siblings are unrelated.

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 exist, so the description carries full burden. It only states basic functionality but omits behavioral traits like search behavior on no results, pagination, or read-only nature.

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

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

The description is a single concise sentence that front-loads the purpose. It could incorporate more detail without losing conciseness, but is 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 search tool with no output schema and minimal annotations, the description lacks details on how search results are returned, ordering, or the effect of the limit parameter. Incomplete for effective 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 50% with only query described; the tool description adds no additional parameter information. The limit parameter is undocumented both in schema and description, leaving the agent without needed context.

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 (search) and scope (all files of current user), which distinguishes it from sibling tools like list_files (which lists without filtering). However, it lacks explicit differentiation, so not a 5.

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

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

No guidance on when to use search vs. list_files or other alternatives. No prerequisites or context for usage provided.

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

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

No annotations are provided, so the description carries the full burden. It discloses idempotency ('安全 (服务端幂等写临时块)') and concurrency safety. It does not detail error handling, rate limits, or response behavior, but the core behavioral traits are covered.

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

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

The description is extremely concise, with only three lines. It front-loads the purpose and step number, then adds critical usage notes. Every sentence earns its place, no superfluous content.

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 is part of a 3-step upload process, the description provides enough context for an AI agent to understand sequencing, concurrency, and idempotency. However, the absence of an output schema leaves the agent uninformed about the response, which is a minor gap.

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

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

Schema description coverage is 100% (all three parameters have descriptions). The description adds contextual value (concurrency, retry, idempotency) but does not enhance parameter semantics beyond what the schema already provides. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: '上传单个分片 (第 2 步 / 共 3 步)' (upload a single chunk, step 2 of 3). It distinguishes itself from sibling tools like upload_init and upload_complete by specifying its place in the workflow.

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 mentions that calls can be concurrent and that the same chunk_index can be retried on network jitter. This provides clear usage context. However, it does not explicitly state when not to use this tool or provide alternatives beyond the implied step sequence.

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 fully discloses behavioral traits: direct path uses OSS CompleteMultipartUpload and avoids ECS memory/bandwidth, relay path merges from temporary shards, and return metadata. No contradictions.

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

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

Description is concise and well-structured with clear sections for the two paths. However, use of Chinese mixed with English may reduce clarity for some agents. Otherwise efficient.

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

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

Given no output schema, description sufficiently specifies return metadata (id, uuid, etc.). Tool has only 2 parameters both well-described. Complete for its 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 100%, so baseline is 3. Description adds flow context but does not significantly enhance parameter meaning beyond the schema's already detailed 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 explicitly states it's step 3 of 3 for merging shards and outlines two clear paths (direct and relay) with their purposes. Verb+resource is specific and actionable.

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

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

Description explains when to use each path (direct vs relay) based on whether 'parts' are provided, catering to different clients (shim vs web). Lacks explicit when-not 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?

No annotations provided, so description carries full burden. Discloses quota consumption and credit deduction. Warns about unnecessary uploads. Mentions size limit (<20MB) and reuse of init+chunk+complete pattern. Could include overwrite behavior or error handling, but sufficient for typical use.

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 bulleted format in Chinese. Front-loaded with main purpose. Every sentence adds valuable information 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?

Given 5 parameters and no output schema, the description covers key constraints: when to use, size limits, quota impact, and folder support. Lacks return value description but is generally complete for an upload operation.

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

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

Schema coverage is high (80%), so baseline is 3. Description adds minimal value beyond schema: mentions folder_path default '/' and the init+chunk+complete workflow, but most parameter details are already in schema.

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

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

The description clearly states '上传一个文件（base64 形式）到用户的文件中转站', identifying the action (upload), resource (file), and format (base64). It effectively distinguishes from sibling tools like upload_chunk, upload_init, upload_complete which handle partial steps.

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 call: only when user explicitly requests to save/transfer/share files. Also provides clear exclusions: do not upload intermediate results, logs, or unsaved command outputs. Suggests alternative for large files using web chunked 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, so description carries burden. Discloses return behavior (instant metadata vs session info). Missing details on side effects, idempotency, or authorization needs.

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?

Very concise two-sentence structure with bullet points for clarity. Every sentence serves a purpose.

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

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

Given no output schema and 6 parameters, description adequately covers the workflow and branching logic. Could mention expected response shape for instant=false.

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 83%; descriptions already cover most parameters. Description adds no new parameter-specific detail beyond what schema provides.

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

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

Description clearly states it initiates a multipart upload session (step 1 of 3), with distinct verbs and resource. Differentiates from siblings by naming upload_chunk and upload_complete.

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 frames when to use (first step) and outlines two branching scenarios (instant vs non-instant) with follow-up steps. Lacks explicit when-not-to-use but sufficient for workflow.

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 bears full burden. It discloses limits (file count, size), auto-numbering, and the 15-minute download URL validity. Missing details about error handling or input validation.

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

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

Two sentences: first states primary purpose, second lists constraints. Every sentence adds essential information, 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?

No output schema exists, so description must imply return value. It mentions '返 15 分钟下载 URL' (returns 15-minute download URL), covering the key outcome. Together with parameter descriptions and limits, it is fully adequate for this 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 coverage is 100%, but the description adds value by explaining '同名文件自动加序号' (auto-number duplicate names) and '自动补 .zip' (auto-append .zip extension), which are not in the schema.

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

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

The description clearly states the tool's purpose: '把多个文件打包成一个 ZIP' (zip multiple files into a ZIP). It distinguishes from sibling tools like upload_file or download_file by specifying it's a compression utility that generates a download URL.

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 limits (50 files, 200MB original size) and behavior for duplicate names (auto-numbering). However, it lacks explicit guidance on when not to use this tool or alternatives, though the limits serve as constraints.

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