扫描书库

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'sample check text layer' and 'generate inventory/suggested output', but does not explicitly state whether files are modified, whether output directories are created, or whether the scan is read-only. This leaves ambiguity about side effects. While 'scanning' implies non-destructive, the generation of output is underspecified.

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 a single, efficient sentence that is front-loaded with the main action ('recursively scan'). Every phrase adds meaning, and there is no fluff or repetition. It is appropriately sized for the tool's complexity.

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 4 parameters, no annotations, and an output schema (which reduces the need to explain return values). However, the description lacks explicit usage guidance (when to use vs alternatives), fails to mention 'max_files', and leaves behavioral transparency gaps (e.g., file modification). While it covers core purpose and some parameters, it is not fully complete for an agent to reliably invoke it in all contexts.

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 0%, so the description must compensate. It partially covers 'root' (directory to scan), 'output_dir' (suggested output directory), and 'inspect_pages' (sampling pages), but 'max_files' is not mentioned at all. The description does not clearly define parameter specifics or relationships, leaving gaps for an AI agent to correctly set parameters.

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 ('scan') with a clear resource ('PDF books in directory'), and states specific actions: recursive scanning, sampling text layer, generating inventory and suggested output directory. This clearly distinguishes it from sibling tools like 'inspect_pdf_text_layer' or 'batch_extract_library'. The title in Chinese also aligns with the purpose.

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 the tool is for initial library scanning/inventory generation but does not explicitly state when to use it over alternatives. No exclusions or alternative tool recommendations are given. The context of 'recursively scanning a directory' is clear, but explicit usage guidance is missing.

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