pixelize

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

No annotations are provided, so the description carries the full behavioral burden. It discloses a lot of algorithmic behavior (OKLab palette reduction, specks/orphan cleaning, grid-line drift handling, background auto-removal only when there is no transparency), which is genuinely useful. It is silent on overwrite semantics, what happens on failure, whether the source image is modified, and where output paths resolve, though, so gaps remain for a file-mutating 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?

Front-loaded with the one-line purpose, then a compact block of behavioral context, then terse per-parameter glosses with no wasted words. Dense but every line carries signal. The parameter list format is scannable, though the paragraph on grid detection is slightly heavy for what it adds.

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?

No output schema exists, and the description handles that by stating the return value (a report plus a source|result preview). Combined with mode-selection and parameter glosses, an agent has enough to invoke it correctly. Missing overwrite/failure semantics keep it from being complete for a mutating 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 description coverage is 0% across 12 parameters, so the description must compensate, and it does for the five non-obvious ones: cell, target_height, background, outline, palette_from. image, output, layer, and overwrite are self-evident from their names. max_colors, merge_delta, and png_output are undocumented in both schema and description, which keeps it below 4.5.

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 and resource chain: convert an image into pixel art and save it as a native-resolution .aseprite. No sibling tool (export, import_strip, apply) does this, so the agent can distinguish it from every other tool in the set without opening a 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?

Clearly explains the three modes: fake-grid detection, real illustration downscale, or explicit target_height. That tells the agent which path fires for which input. It stops short of naming sibling alternatives (e.g. when to use export + import_strip instead), so it is 4 rather than 5.

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