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

The description and schema surface behaviors beyond annotations: batch limits (up to 20), ZIP return with per-file errors, tier requirements, the broken watermarkTile path with clear remediation, signature handling modes, and conditional parameter semantics ('read only when...'). This is rich behavioral disclosure and contradicts no annotation.

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 tight one-liner which covers the essential purpose, scope, and output shape. It is front-loaded with the action and batch limit; however, the parameter-level descriptions inside the schema are necessarily verbose, so the overall tool definition is long due to schema, not due to redundant prose.

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 21-parameter batch tool with no output schema, the description plus fully described input schema covers invocation, limits, error handling, tier restrictions, broken paths, and output format. The only minor gap is that it does not separately define the return structure beyond 'ZIP with each flattened file (and per-file error entries)', but that is sufficient for an agent to select and call it.

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 100%, so the schema already documents every parameter. The description itself adds batch framing and output details but doesn't re-document params; it wisely lets the schema carry that weight. A 4 reflects the strong schema coverage plus the added top-level context.

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 begins with a specific verb and resource ('Flatten PDFs (Batch)') and immediately states the batch scope: apply the same configuration to up to 20 PDFs in one request. It also names the output contract (ZIP with flattened files and per-file error entries). The [category: pdf] tag and sibling list further disambiguate it from pdf_flatten and pdf_watermark.

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 explicitly explains the batch use case vs alternatives, and the schema provides conditional signals (e.g., 'watermarkTile' says to use pdf_watermark instead, 'ocrFirst' requires Starter+, 'mode: none' is for OCR/watermark/PDFA-only pipelines). The sibling context includes pdf_flatten and pdf_watermark, and this description clearly distinguishes the batch path.

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