pdf_extract_images

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the return value ('Returns the file list'), default output directory, and the min_dimension filtering behavior. It does not mention whether the operation is read-only (obvious for extraction), file overwrite behavior, or error conditions, but the given details are substantive and sufficient for basic usage.

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 efficient and well-structured. It opens with the core purpose, then lists parameter explanations in a compact Args block. Every sentence earns its place—no fluff. It is front-loaded with the action and returns a brief note on next steps, making it easy to scan.

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 4 parameters, an output schema, and a clear workflow, the description covers all necessary aspects: purpose, parameter semantics, expected output, and integration with sibling tools. It omits minor details like error handling or output dir creation, but the output schema provides return structure, and the description gives enough to call the tool correctly without ambiguity.

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 explain all parameters, and it does thoroughly. It defines source as 'Local file path or direct http(s) URL', pages as page selection like '1-5' with empty meaning whole document, output_dir with a default, and min_dimension with its purpose. This adds clear meaning beyond the bare schema titles 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 clearly states the specific action: 'Extract embedded raster images (figures, photos) from a PDF to files on disk.' This uses a precise verb and resource, and the mention of 'raster images' and saving to disk differentiates it from other PDF tools like pdf_read, pdf_view, and pdf_ocr. The follow-up hint to use image_view also helps distinguish its role.

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 provides usage context by stating it extracts images and suggests using image_view afterwards for inspection. However, it does not explicitly mention when not to use this tool or compare it with other PDF tools like pdf_info or pdf_ocr. The purpose inherently implies when to use it, but lacks explicit exclusions or alternative selection criteria.

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