PDF to images

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

Annotations cover the safety profile (readOnly, idempotent, closed-world), and the description adds genuinely non-obvious behavior: the 16384 px / 16.7 MP per-page cap, that the output folder is created if missing, and that password-protected PDFs are handled. It stops short of saying what the tool returns (a path list?) and whether existing files in the target folder are overwritten.

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?

Dense and front-loaded: the core action and output naming come first, then the tunable options, then the size cap. The trailing web-version URL is minor filler but only one clause.

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?

With no output schema, the description still communicates the return shape via the per-page filename convention and output-folder default, and it warns about size capping. Missing only the overwrite/collision behavior and whether a manifest of written files is returned — minor for an 8-param, 1-required tool.

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 100%, so baseline is 3; the description earns extra by giving DPI guidance the schema lacks (72 = screen, 150 = default, 300 = print) and by tying quality to JPEG/WebP and transparency to PNG/WebP. The page-range and file/password semantics are left entirely to the schema.

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?

Opens with a specific verb+resource+output: "Render PDF pages to PNG, JPEG or WebP images in a folder." It also states the output shape (one file per page, named <name>-p001.png), which distinguishes it from reverse-direction siblings like pdf_from_images and text-extraction siblings like pdf_to_text / ai_pdf_to_markdown.

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?

Usage is only implied by the option list (DPI presets, page range, transparency) — the agent can infer this is the tool for rasterizing pages. There is no explicit when-to-use/when-not statement and no routing against alternatives such as ai_pdf_to_markdown (text) or image_convert (already-raster images).

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