preview

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

No annotations are supplied, so the description carries the full burden. It discloses rendering behavior (zoom, checkerboard transparency, pixel grid, default scale fitting maxSize) but never states the return form (presumably an image), whether the tool is read-only, or what happens with invalid paths, leaving real gaps for an 11-parameter tool.

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?

It is short and front-loads the core behavior, but the telegraphic fragment style ("frames="all" contact sheet; tags=true one row per animation") compresses to the point of ambiguity and forces re-reading.

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 11 parameters, no annotations, no output schema, and 27% schema coverage, the description should carry more. It omits the return type entirely and says nothing about five parameters, leaving too much for the agent to infer before calling.

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 only 27%, and the description adds meaning for about five of eleven parameters (frames, tags, tag, reference, referenceRect). It leaves path, grid, frame, layer, and scale unexplained beyond the bare schema types, so it compensates only partially for the coverage gap.

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?

"See the sprite: zoomed, checkerboard transparency, pixel grid" names a concrete resource and the rendering features, so an agent knows this produces a visual preview rather than data. It never differentiates itself from siblings like read_pixels, export, or sprite_info, which prevents a 5.

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 covers option-level usage (frames="all" for a contact sheet, tags=true for one row per animation, tag=name) and a specific workflow for reference images ("check every pass against it"), but says nothing about when to call preview instead of read_pixels, sprite_info, or export.

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