Convert handwritten or sketched canvas content into structured text and LaTeX, using local VLM/OCR when available, and record recognition results for session recall.
【递纸】对手写画布做结构化识别（若已配置本地 VLM/PaddleOCR-VL/GLM-OCR 则输出中文文本与 LaTeX；否则回退为让 Agent 直接看图）。同时把识别结果记入当前会话，便于回溯。
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does 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 that behavior depends on local VLM/OCR configuration, that it may fall back to Agent image inspection, and that results are recorded in the current session for traceability. It does not cover all edge-case behaviors but provides meaningful transparency beyond the bare tool name.
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 and front-loaded with the core purpose, then covers fallback and side effects in one dense sentence. However, the leading '【递纸】' is unexplained jargon that could confuse an AI agent, and the single-sentence structure packs several ideas together.
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 zero-parameter tool with no output schema, the description is reasonably complete: it states what the tool produces, when it falls back, and that it persists the result to the session. It could be improved by clarifying prerequisites like whether a handwriting canvas must already exist and what the structured result format looks like, but those are not critical gaps.
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 tool has zero parameters and the schema description coverage is 100%, so there are no parameter semantics to document. The baseline of 4 applies, and the description appropriately does not try to invent parameter information.
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 identifies the action ('做结构化识别' on the handwriting canvas) and specifies the expected outputs (Chinese text and LaTeX) with a fallback to letting the Agent view the image. This distinguishes it from siblings like get_handwriting, which presumably retrieves the raw canvas, and get_handwriting_status, which checks status.
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 explains the conditional behavior: use configured local VLM/OCR for structured output, otherwise fall back to Agent direct image viewing. It implies when this tool is appropriate but does not explicitly mention exclusions or directly name sibling alternatives, leaving some inference to the user.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.