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

Annotations only declare read-only/idempotent/non-destructive/closed-world; the description adds substantial behavior the agent could not otherwise know: the return shape in both modes, the 8-artboard cap, what captions contain (size, content_bbox with tight bounds and fill≈%), and the preflight severity model where off-center blocks Variants/Directions while brush and size findings are advisory. That is real consequence disclosure rather than restating the safety hints.

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?

Front-loaded with the core action and mode split, and nearly every clause carries operative information. It is a single dense paragraph mixing return shape, caption fields, and preflight policy, which makes it heavier to scan than it needs to be, but there is little filler.

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 correctly carries the burden of explaining return values, the artboard list, caption contents, and preflight semantics. The one gap is that it references fix_preflight: true / "all" as the remedy for findings, but fix_preflight is not among this tool's parameters (additionalProperties is false), so an agent may try to pass it here and fail; that reference needs an owner tool named.

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 all three parameters are already documented in the schema, including the artboard_id/artboard_name alternative and the UUID format. The description reinforces when each applies but adds little syntax or format meaning beyond the schema, so the baseline applies.

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 and resource ("Fetch a library asset by id") and then explicitly separates the two modes — single-artboard flattened PNG vs multi-artboard MagicPixel documents with an artboard list plus up to 8 artboard PNGs. It also disambiguates against a common misreading ("NOT a packed spritesheet") and names the id source (list_assets), so an agent can place it among the get_* siblings.

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?

Gives explicit selection rules: omit artboard_id/artboard_name for single-artboard assets, pass one of them to pick a sprite in multi-artboard files. It also states a downstream usage (reuse artboard size as generate_pixel_art.size). It stops short of saying when to prefer get_marketplace_asset or listing preconditions, so it is clear but not exhaustive.

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