pdf_split

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

No annotations are present, so the description must carry the full behavioral burden. It discloses one useful trait: the 1-cent cost. But it does not say what happens to the original file, whether output is returned or written to output_path, whether the API mutates anything, or any quotas/limits. This is insufficient for a tool with zero annotation support.

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: the operation comes first, followed by high-value range syntax and cost. No wasted words. Retaining the cost line and range example is useful, though a sentence explaining output_path would add much more practical value.

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 tool with four parameters, no output schema, and zero annotations, this annotation is not complete enough to allow safe and accurate invocation. The agent must infer output_path requirements and idempotency semantics, and the description gives no clue how the extracted PDF is returned or saved. The helper page extraction is clear, but the surrounding operational details are missing.

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%, and the description only explains the pages parameter through an example range. It does not clarify that file is a PDF path, what output_path should be, or what idempotency_key does. With four parameters remaining largely undocumented, the description fails to compensate for the schema's lack of description.

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 a clear verb and resource combination: 'Extract pages from a PDF.' The page-range example makes the operation concrete and unambiguous, and it differentiates this tool from siblings like pdf_merge, pdf_rotate, and pdf_compress, which do not extract subsets of pages.

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 guidance about when to choose this tool over its alternatives, and no conditions for when not to use it. The page-range syntax implies a usage flow, but the description never states how to decide between pdf_split and pdf_rotate, pdf_merge, or pdf_to_images. That leaves much of the tool-selection work to inference.

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