Look at the sprite

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

The description discloses substantial behavioral details absent from the annotations: preview is a nearest-neighbour upscaled PNG around 1024px, ascii is capped at 64×64 and includes a colour legend and rulers, filmstrip composites every frame because vision models only read the first frame of a GIF, and diff uses specific glyphs for unchanged/erased/changed pixels. These details go far beyond the readOnlyHint and openWorldHint annotations and help the agent predict exact tool behavior.

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?

The description is long but tightly organized as a bullet list where each operation is a single line with purpose and output. The opening one-liner sets scope, the ops cover the full tool vocabulary, and the closing workflow sentence ('Draw, then look, then fix') earns its place by reinforcing when to invoke the tool. No filler is present.

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?

Given the tool has 8 parameters, an output schema, and read-only annotations, the description covers the essential operational context: what each op returns, when to use each, size limits, and a recommended loop. The description is complete enough for an agent to select and invoke the tool correctly without needing supplementary documentation.

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 high at 88%, so the schema already documents most parameters. The description adds significant semantic value by explaining what each op value means and how parameters like region interact with ascii's size cap. It stops short of explaining every parameter's edge case, but the combination of schema and description is strong.

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 opens with a clear verb and resource ('See what is actually on the canvas') and then enumerates four concrete operations with distinct outputs: preview, ascii, filmstrip, and diff. This clearly distinguishes the tool from siblings like read_pixels and validate by scoping it to visual inspection of the sprite/canvas.

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?

Every operation is paired with an explicit use case ('Use for overall read', 'Use to verify precise pixel positions', 'The only reliable way to review an animation', 'Use it to confirm exactly what an edit touched'). The description also gives a workflow directive ('Draw, then look, then fix') and warns against reporting a sprite finished without looking, making selection criteria explicit.

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