Detect pixel differences between two sprite frames or files, returning the changed pixel count and bounding box so you can verify whether a part moved; zero changed pixels confirms no movement.
Pixel difference between two frames (of one sprite, or of two files): changed pixel count and the box that changed. 0 changed pixels proves a part did not move.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| layer | No | ||
| region | No | ||
| frame_a | Yes | ||
| frame_b | Yes | ||
| other_path | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the return semantics (changed pixel count and the changed-box) and the interpretation of a zero result, but says nothing about read-only nature, permissions, or cost/limits.
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?
Two tight sentences, front-loaded with the core operation and return values, with zero 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?
No output schema exists, and the description does cover the return shape (count plus box), which is helpful. But for a 6-parameter tool with no annotation or schema documentation, leaving layer and region undefined is a real gap.
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 0%, so the description must compensate. The parenthetical '(of one sprite, or of two files)' implicitly explains other_path versus a single path, but layer and region — two of the six parameters — get no mention at all.
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 (pixel difference) and resource (two frames) plus the two supported modes (one sprite's frames vs. two files) and what it returns. An agent can distinguish it from siblings like check_identity or find_glitches, though it never explicitly names those alternatives.
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?
Usage is only implied: '0 changed pixels proves a part did not move' hints at a verification use case, but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as read_pixels or check_identity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.