Read pixels as text

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

Annotations provide readOnlyHint=true, and the description does not contradict it. It adds valuable behavioral details beyond the annotation: transparency represented as '.', trailing '.' cut off, max call size, and layer flattening rules. These are exactly the kind of operational traits an agent needs and are not in the annotations.

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?

Three sentences, no wasted words. The core purpose and format are front-loaded, followed by key behavioral notes. Each sentence earns its place, covering purpose, format, layer behavior, palette guidance, and limits.

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?

For a read-only tool with a comprehensive schema and readOnly annotation, this description covers the essential operational knowledge: output format, interpretation of transparency, maximum pixels, and layer/palette behavior. Missing error handling details are minor for this type of tool, and no output schema exists so the description appropriately explains the return format.

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% — every parameter is described with defaults and formats. The description adds the 'same keys back' hint and the max pixel constraint, which are useful but not substantial. Since the schema already carries the semantic weight, the description's contribution is modest, warranting the baseline of 3.

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 clearly states a specific verb (reads), resource (pixels), and output format (palette + rows), with a concrete use case (inspect colors, copy/modify). It references aseprite_pixel_map but doesn't explicitly contrast itself against that sibling, though the 'reads back' wording implies a read vs. write distinction.

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 explains when to use the tool (inspect exact colors, cheap copy/modify) and provides key context: layer behavior (visible flattened vs. specific layer), palette passing for consistent keys, and a 16384-pixel cap. No explicit exclusions or alternative routing, but the read purpose is self-evident from the name and description.

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