Tool Batch Ocr

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

With no annotations provided, the description must carry full behavioral disclosure. It clearly discloses the write-back nature, per-file result returning, and failure isolation. However, it does not clarify whether files are overwritten in place, how out_dir relates to write-back, or how redo_ocr/overwrite/retries/timeouts affect behavior, leaving operational side effects under-specified.

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, front-loaded with the main action and scope, and no filler or repetition. Every phrase contributes useful information.

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?

Despite the presence of an output schema, the tool has 8 parameters and no annotations or schema descriptions. The description covers the required input and failure handling but leaves essential operational details like write destination, overwrite behavior, and advanced options unexplained, so an agent can make a default call but cannot confidently handle non-default use cases.

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 for all parameters. It only explains 'inputs' as file paths or directories taking all PDFs; the other seven parameters (lang, deskew, out_dir, redo_ocr, overwerite, max_retries, per_file_timeout) are left without meaningful semantics beyond their names and defaults.

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 opens with '批量 OCR 写回' (batch OCR write-back), which identifies a concrete action and resource, then specifies that inputs can be file paths or directories containing all PDFs. This distinguishes it from the single-file sibling tool_ocr_pdf via the 'batch' and 'per-file' framing, though it does not fully define the write-back target.

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 input guidance about directories and all PDFs, plus the statement that a single-file failure does not interrupt the batch, implies the intended use case for batch OCR over multiple files. However, no alternatives are named and there is no explicit when-to-use vs when-not-to-use guidance relative to the many sibling tools.

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