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

The description only states the action and output, adding no behavioral detail beyond what the annotations already provide. It does not mention that new files are created while the original is left intact, whether processing is synchronous, or any permission requirements. Since annotations are present but the description adds no extra context, this is a weak score.

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, front-loaded sentence with no wasted words. It efficiently conveys the core purpose without unnecessary elaboration.

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 tool with full schema descriptions, an output schema, and safety annotations, the minimal description is adequate for basic invocation. However, it does not clarify edge cases like behavior when pages_per_file exceeds total pages or how the tool relates to extract_pages, leaving some ambiguity in tool selection.

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 has 100% description coverage, including a clear description for pages_per_file ('default 1: one file per page'). The description adds no additional parameter meaning, so the baseline of 3 is appropriate.

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 ('split') and resource ('PDF'), clearly stating that the output is several smaller PDFs. This differentiates it from siblings like compress or rotate, though it does not explicitly distinguish it from extract_pages, which could also produce smaller PDFs.

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 guidance on when to use this tool versus alternatives. It does not mention extract_pages, merge_pdfs, or any other sibling, nor does it provide context like 'use this to divide a PDF into chunks' or 'if you need specific page ranges, use extract_pages instead.'

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