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

Annotations already establish read-only, non-destructive, closed-world behavior, and the description adds genuinely new traits: CSS that only the browser draws is omitted from the render, JPEG is chosen automatically when photos dominate, and output is capped (10 pictures, 50 per contact sheet). The token-cost estimates per width tier are the kind of budget information no annotation or schema field carries.

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?

Output format and scope are front-loaded, and every sentence carries operational or cost information with no filler. The parenthetical 'css only the browser draws is left out, and check names it' is telegraphic to the point of near-unreadability, which costs it a point.

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 does the work of explaining what comes back (PNG/JPEG images, one per slide or a single contact sheet), plus limits, defaults and cost. It still leaves unclear how the images are returned to the agent or what happens on partial/render failure.

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 the schema baseline alone would be a 3; the description adds real meaning by tying width to token cost (1280 per slide vs 1600 for a contact sheet) and by stating the contact-sheet cap of 50, which the schema's '10 at most' array limit does not convey. It adds little about `build`, leaving that 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?

The description states a concrete verb+resource: it turns slides into PNG/JPEG images that look exactly as people see them, which distinguishes it from text-oriented siblings like read or get. It points at `check` for CSS naming but never contrasts itself with export_slides, the sibling most likely to be confused with rendering pictures.

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 gives clear context: use this to judge visual looks (crowding, balance, pictures, contrast), and the per-image vs contact-sheet token costs implicitly tell the agent when to browse broadly versus inspect one slide. It stops short of explicit exclusions, so there is no statement of when to prefer export_slides or read instead.

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