stagenth · 文档解析

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

With no annotations, the description carries the full burden. It discloses the chunking algorithm (by heading hierarchy, subdividing long chunks by paragraphs) and the return format. However, it does not mention side effects, non-destructive nature, input constraints, or error behavior, leaving gaps in behavioral disclosure.

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, front-loaded with purpose and method, followed by return format and benefit. Every sentence earns its place with no unnecessary 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?

For a simple chunking tool, the description is fairly complete: it covers purpose, behavior, and output format. Schema descriptions cover all parameters. Minor gaps remain around edge cases (e.g., both file_id and data_base64 null, file type limitations) and alternative usage, but overall it is sufficient given the schema richness.

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 5 parameters, so the baseline is 3. The description adds minimal parameter-related context (e.g., chunking rules relate to max_chars), but mostly relies on the schema's parameter descriptions. No additional parameter semantics are 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?

The description uses a specific verb '切成' (cut into) with the resource '文档' (documents), and clearly states the scope: creating semantic chunks for RAG/vector embeddings. It distinguishes from sibling tools (doc_images, doc_parse, doc_tables) by focusing on chunking rather than images, parsing, or tables.

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 mentions when to use it ('喂检索/嵌入' – for retrieval/embedding) and highlights the benefit of not writing custom chunking logic. It does not explicitly list exclusions or compare with alternatives, but the context is clear enough for RAG/embedding workflows.

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 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.

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

With no annotations, the description carries the full burden and delivers by disclosing billing (per-page credits), the pure-parsing nature, lack of OCR support, and page_range behavior. These details go well beyond a basic purpose statement and set accurate expectations.

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 compact, using three sentences to cover capabilities, limitations, and billing. Every sentence provides value, with no fluff or repetition.

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 tool has no output schema, and the description explains input formats, limitations, and billing, but it leaves the term 'structured' undefined. Given the moderate complexity and the existence of sibling tools, the description is sufficiently complete for an agent to select and invoke the tool 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?

The input schema already describes all 5 parameters with 100% coverage, so the baseline is 3. The description adds billing semantics tied to parsed pages, which enriches the meaning of max_pages and page_range beyond the schema's syntax-level 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?

The description clearly states the tool parses PDF/Word/PPT/HTML/plain text into clean Markdown and structured format, using a specific verb and listing supported file types. It distinguishes itself from sibling tools by emphasizing full-document parsing and conversion rather than AI content generation.

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 provides clear context about pure parsing (no AI content) and the OCR limitation, which tells users when not to use it. However, it does not explicitly mention alternatives like doc_chunk, doc_images, or doc_tables, so it falls short of a full usage guide.

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 the output format (headers+rows JSON, directly computable) and mentions PDF layout recognition, adding behavioral context. However, it does not address potential limitations such as handling of files without tables, failure modes, or processing constraints beyond the schema's max_pages parameter.

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, front-loaded with the core purpose and output format. The second sentence efficiently adds sibling differentiation and PDF-specific behavior. 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?

The tool is moderately complex with 4 parameters and no output schema. The description covers the return format (headers+rows JSON) and the core use case, making it fairly complete. It lacks details on edge cases (e.g., no tables found, file size limits) but remains adequate for typical 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 description coverage is 100%, so the baseline is 3. The description adds marginal parameter-related context by noting PDF uses layout recognition, which relates to max_pages, but does not explain parameter interactions or provide additional syntax/format details 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 extracts tables from PDF/.docx/.pptx and converts them to structured headers+rows JSON. It distinguishes itself from the sibling doc_parse by explicitly contrasting the structured output with flattened markdown pipe text.

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 use case (direct computation) and explicitly contrasts with doc_parse, naming the alternative tool. However, it does not mention when to use doc_tables over doc_chunk or doc_images, nor does it state when not to use it beyond the doc_parse distinction.

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