Download files or images from a current project work item, returning images directly and other files as Base64; optionally save them to a local path for later viewing.
认证下载当前项目工作项中的文件或图片。图片直接返回图像内容；其他文件返回 Base64。可传 save_to 将文件保存到本地（目录或完整路径），返回的 path 可用 view_image 等工具查看。仅支持描述等富文本中的 fileIdentifier，最大 10 MiB。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | Yes | ||
| save_to | No | 本地保存路径；目录或完整文件名。省略则直接返回文件内容。 | |
| workitem_id | Yes |
Changes observed during successful MCP inspections.
v0.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the readOnlyHint annotation: states authentication is required, that images are returned as content while other files come back Base64, that save_to writes to a local directory or full path and returns a usable path, and that the 10 MiB cap applies. It also discloses the input-source restriction (fileIdentifier from rich text). Note that the local write implied by save_to is a side effect the annotation does not capture, but it does not modify remote project data, so this is not a contradiction.
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 short clauses, front-loaded with the core action, then return format, then save_to behavior, then the input/size constraints. Dense but every sentence carries information; nothing is redundant with the schema.
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, the description correctly spells out the two return shapes (image content vs Base64) and the path returned when save_to is used, plus the size ceiling. Remaining gaps are minor: what happens when a file exceeds 10 MiB, and whether the project is implicit from session 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 only 33% (workitem_id and file_id are bare patterned strings), so the description must compensate, and it does for file_id by tying it to the fileIdentifier embedded in rich text. save_to semantics (directory vs full filename, omitting it returns content inline) are stated in both places. workitem_id's relationship to the containing work item is only implied.
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?
Uses a specific verb+resource: '认证下载当前项目工作项中的文件或图片', and immediately says what comes back (image content vs Base64). No sibling tool returns files, so differentiation is implicit rather than stated, which keeps it just 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?
Clear context for when to call it: only when you have a fileIdentifier taken from rich text such as a work-item description, and only for files under 10 MiB. No alternative-tool routing is needed here because nothing else in the sibling list fetches files, but the description never states that explicitly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.