read_pdf_textExtract body text from downloaded local PDFs using a file path or cached paper label, with start and max character limits to page through long papers locally without CNKI access or verification.
读取已下载 PDF 的正文。纯本地操作，不访问知网，不会触发任何验证。
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | 本地 PDF 的绝对路径，或 list_cached_papers 返回的论文标签（cnki:…） | |
| max_chars | No | 本次最多返回的字符数 | |
| start_char | No | 起始字符位置，从 0 开始 |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.32.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the key behavioral trait: no network access to CNKI and no verification triggered, which is exactly the risk an agent cares about here. It stops short of other relevant traits — what happens on a scanned PDF with no text layer, whether truncation is signalled when max_chars is hit, and failure behavior for a bad path.
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?
Two short sentences, the core action front-loaded, and the safety constraint immediately after. Nothing redundant or padded.
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?
An output schema exists, so return values needn't be explained, and the tool is simple. But the surrounding family contains two closely overlapping readers (read_paper_fulltext, read_paper_pdf) plus read_papers_batch, and the description gives no basis for choosing among them — the main missing piece for correct invocation.
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 file_path (absolute local path or cnki: tag), max_chars and start_char are all fully documented in the schema. The description adds only the implicit hint that file_path points at something already downloaded. Baseline 3 applies.
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?
States a specific verb and resource: read the body text of an already-downloaded PDF. The 'already downloaded' qualifier usefully scopes it. However, it never distinguishes itself from the near-identical siblings read_paper_fulltext and read_paper_pdf, so an agent cannot tell from this text which one to open.
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?
There is no explicit 'use this when…' or mention of the alternatives. The clause 'pure local operation, does not access CNKI, does not trigger verification' implies the usage condition (call this when you want to avoid hitting CNKI/anti-bot flows), but the agent must infer that and is given no routing rule against the sibling readers.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.