上传单个分片 (第 2 步 / 共 3 步)。
可并发调用, 后端内部会记录已上传索引。网络抖动重试同一 chunk_index
安全 (服务端幂等写临时块)。
| Name | Required | Description | Default |
|---|---|---|---|
| chunk_index | Yes | 分片索引 (0-based), 最后一片索引 = total_chunks-1 | |
| data_base64 | Yes | 本片字节的 base64 编码。每片大小应等于 upload_init 返回的 chunk_size, 最后一片可能短。单次调用建议 <12MB base64 (约 8-9MB 原字节)。 | |
| session_uuid | Yes | upload_init 返回的会话 UUID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description takes on the full burden of behavioral disclosure. It reveals key traits: concurrent calls are allowed, the backend tracks uploaded indices, and retrying the same chunk_index is safe due to idempotent temporary writes. This goes beyond basic operation description, though it omits authentication requirements and error behaviors.
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 lead line identifying the step, followed by two short sentences covering concurrency, backend state, and idempotency. Every sentence carries unique value, with no redundancy or filler. The structure front-loads the most critical purpose 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?
The description effectively covers the essential context for a chunked upload step: its place in the workflow, concurrency behavior, retry semantics, and server-side idempotency. While there is no output schema and the description doesn't mention return values, this step is simple enough (upload one chunk) that the provided details are sufficient for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for all 3 parameters, so the schema fully documents each parameter's type, constraints, and meaning. The description adds no additional parameter semantics—it only reinforces the retry safety for chunk_index, which is already implied by the schema's 0-based index. 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 specifies '上传单个分片' (upload a single chunk) and places it as '第 2 步 / 共 3 步' (step 2 of 3), clearly defining the verb, resource, and its position in a multi-step process. This distinguishes it from sibling tools like upload_init and upload_complete, making the 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?
It clearly states this is step 2 of a 3-step process, implying usage after upload_init and before upload_complete. It also provides explicit guidance on concurrency and retry safety ('可并发调用', '网络抖动重试同一 chunk_index 安全'), which tells the agent when and how to reuse the tool. However, it does not explicitly mention alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are largely distinct with clear purposes. Some potential confusion exists between upload_file (a convenience wrapper) and the upload_init/chunk/complete sequence, but descriptions help clarify. The inclusion of scrape_url feels out of place but is also distinct.
Most tools follow a consistent verb_noun pattern (e.g., create_folder, delete_file, download_file). However, 'file_read' breaks the pattern (should be read_file), and 'get_file_info' uses get_ while others use list_. Overall minor inconsistency.
With 25 tools, the count is slightly high but still reasonable for a file management server that includes upload, download, sharing, and folder operations. A few tools (like scrape_url) seem tangential, but overall the scope justifies the count.
The tool surface covers most core file and folder operations (create, read, update/move, delete, list, search, upload, download, share, zip). Notable gaps include no rename_file tool and no ability to update file metadata. Still, the set is fairly complete for basic file management.