压缩图片、可顺带换格式（1 credit/次）。产物存文件中转站返下载 URL。失败自动退款。
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | 输出格式 png/jpeg/webp；缺省自动（有透明→webp，否则 jpeg） | |
| file_id | No | 已上传的图片 ID（与 data_base64 二选一） | |
| quality | No | 压缩质量 1-95，越低越小；默认 75 | |
| filename | No | 可选输出文件名 | |
| data_base64 | No | 图片内容 base64（与 file_id 二选一） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden. It discloses per-call credit cost, output stored in a file transfer station with a download URL, and automatic refund on failure—valuable operational facts beyond the basic action. No contradiction with 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 two concise sentences that front-load the purpose, then mention cost, output, and failure handling. No wasted words; each clause adds distinct 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?
For a 5-parameter tool with no output schema, the description provides key context: output is a download URL, there is a credit charge, and failures auto-refund. It does not explicitly mention the required input method, but the schema covers that, making the overall description adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific semantics, but the schema already fully explains each parameter, including defaults and mutual exclusivity.
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 compresses images and optionally converts format, naming the resource (image) and the verb (compress). It distinguishes from format-only conversion by emphasizing compression as primary, though it does not explicitly name sibling tools.
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 usage (when compression with optional format change is needed) and provides cost/output context, but it does not explicitly state when to use this tool versus alternatives like img_convert or img_resize, nor any exclusions.
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.
Most tools are clearly distinct, but img_compress and img_convert both support format changes, and img_info and img_exif both read metadata, creating minor overlap. The descriptions help clarify the primary purposes, so ambiguity is low.
All tools share the img_ prefix and mostly use verb-based names like img_compress and img_resize. However, img_info and img_exif are noun-based, which is a slight deviation from the pattern, though still predictable and readable.
With 8 tools, the server is well-scoped for an image toolbox. Each tool addresses a common operation without unnecessary additions, making the count appropriate for the stated purpose.
The toolset covers the core image lifecycle: inspecting info, reading EXIF, compressing, converting, resizing, cropping, rotating, and watermarking. There are no glaring gaps for a practical image toolbox, so agents can handle typical workflows end-to-end.