pdf_page_layout

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

With no annotations, the description carries the full behavioral burden, and it does so thoroughly. It explains that only page geometry is read, that pages are grouped by shape with page-range notation, that sizes are computed by clipping CropBox to MediaBox and applying /Rotate, and that a 3pt tolerance is used for grouping. It also discloses that per-page output is capped at 100 rows.

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 front-loaded with the core purpose and then delivers dense, useful details about behavior, grouping, parameter formats, and alternatives. Each sentence contributes necessary information, and the final Args block cleanly summarizes the two parameters without redundancy.

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 description covers what the tool returns conceptually, how it handles real-world page size variance, how rotation affects reported sizes, how to request per-page details, and what to use instead for text content. Since an output schema is present, the absence of exhaustive return-field documentation is not a gap.

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, and it does. It explains that 'ref' accepts either a PDF file path or a workspace artifact id, and it defines 'pages' with concrete range formats like '1-20', '3', '1,5,9-12', or 'all', plus the 100-row cap.

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 specific verb and resource: 'Measure a PDF's page sizes, orientation and rotation.' It also frames the tool around concrete questions, which makes its purpose unmistakable. It further distinguishes itself from text-related siblings by explicitly stating it does not look at page content and points to pdf_check_text for that.

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 clearly states when to use this tool: for page geometry and understanding inconsistent sizes or rotation, while noting it stays cheap on long documents. It also gives a direct alternative, pdf_check_text, for readable-text questions, which is an explicit when-not-to-use condition.

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