抽取文档内嵌的图片（PDF / .docx / .pptx），打包 ZIP 落文件中转站并返下载 URL。
过滤 <1KB 的图标噪声；多模态 AI 可配合 doc_parse 的文本一起理解图文文档。
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | No | 已上传到文件中转站的文档 ID（与 data_base64 二选一） | |
| filename | No | 文件名带扩展名；base64 输入时必填以判类型 | |
| max_images | No | 最多抽取图片数（1-100） | |
| data_base64 | No | 文档内容 base64（与 file_id 二选一） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description takes on the full burden. It discloses key behaviors: filters out <1KB icon noise, deposits the ZIP to the file transfer station, and returns a download URL. It also implies a side effect (creating a file in the transfer station) and implicitly a read-only operation on the input. It doesn't cover error handling or rate limits, but given the tool's scope, these are acceptable omissions.
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 sentences. The first is a concise action statement covering the core function. The second adds valuable filtering behavior and a use-case tip. No extraneous words; every sentence serves a purpose. It is front-loaded with the 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?
For a tool with 4 params and no output schema, the description covers the essential context: input formats, output format (ZIP + download URL), filtering behavior, and potential integration with doc_parse. It lacks explicit error scenarios or return value details beyond the URL, but these are not critical for selection. The description is sufficient for typical usage.
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 already provides detailed descriptions for all 4 parameters, achieving 100% coverage. The tool description adds no additional parameter-specific meaning beyond the business context (e.g., file_id relates to the transfer station). Per the rubric, baseline 3 applies when schema coverage is high and the description adds minimal param info.
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 extracts embedded images from PDF/.docx/.pptx documents, packages them into a ZIP, and returns a download URL. It identifies the specific resource (embedded images) and the action (extract), distinguishing it from sibling tools like doc_parse (text extraction) and doc_tables (table extraction).
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 a clear usage scenario: use when you need images from a document, and notes that multimodal AI can combine this with doc_parse's text for understanding image-text documents. It doesn't explicitly exclude alternatives like doc_tables, but the purpose is unambiguous. This constitutes clear context without explicit when-not-to-use guidance.
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.
Each tool targets a distinct aspect of document processing: parsing to Markdown, extracting images, extracting tables, and chunking for RAG. The descriptions clearly differentiate their purposes, and doc_tables explicitly notes its difference from doc_parse.
All tools follow the consistent pattern 'doc_' + a noun (chunk, images, parse, tables). Naming is uniform, lowercase, and underscore-separated, making the tool surface predictable.
Four tools is a well-scoped number for a document parsing server, covering core parsing, image extraction, table extraction, and chunking without unnecessary redundancy.
The tool surface covers the full document processing pipeline: parse to Markdown, extract structured tables, extract images, and produce RAG-ready chunks. The only noted limitation (OCR) is explicitly disclosed and does not undermine the core workflows.