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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds genuine behavioral context: that table extraction is page-scoped and heuristic, that images come bundled in a ZIP rather than loose files. It does not say whether conversions are async, size-limited, or credit-consuming.

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?

Two sentences, front-loaded with the core action and formats, then the routing rule to extract_data. The format enumeration is long but each gloss carries information not evident from the bare enum, so little is wasted.

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?

An output schema exists, so return values need no explanation, and the safety profile is in annotations. However, a 7-parameter conversion tool with four interchangeable-looking input sources and likely async job handling (get_job sibling) leaves an agent guessing on file-source selection and dpi applicability.

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 coverage is 57%, so the description must fill gaps and only partly does: it expands the 'to' enum values (archival PDF/A, grayscale PDF, images as ZIP/PNG/JPEG), which helps pick an enum member. It says nothing about dpi, image_format, or the precedence between file, file_id, file_url, and library_file_id.

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?

States a specific verb (turn) and resource (a PDF) plus the full set of output targets, glossing each format ('PDF/A (archival)', 'images (PNG/JPEG in a ZIP)'). It also explicitly separates itself from extract_data, so an agent can pick correctly without opening either schema.

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?

It names the alternative extract_data and the exact condition that selects it ('tables read by AI, scans, bank statements'), and implicitly contrasts with convert_to_pdf through directionality. It gives no guidance on choosing among the four file-input parameters or on when an async job lookup is needed.

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