What the artist changed

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

The description goes well beyond the readOnlyHint annotation by disclosing the stateful baseline behavior, the exclusion of the agent's own calls, the pixel-map encoding, and the meaning of peek and reset. This is rich behavioral context with no contradiction to 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?

The description is dense but readable, with each sentence contributing a distinct fact and key behavior front-loaded. There is no redundant restatement of the title or schema.

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?

The core watch/diff behavior, return format, and peek/reset flags are fully explained in the absence of an output schema. It is slightly incomplete about what the first call returns and how palette/frame parameters affect the result, but an agent can still invoke it correctly.

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?

The description adds meaning to peek and reset, which have no schema descriptions, and explains the output encoding that relates to palette keys. It relies on the schema for frame, palette, and paletteName, so parameter semantics are well covered across the two sources.

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 identifies a stateful diff tool: it starts watching the active sprite and returns only pixels changed by the artist since the previous call. It distinguishes itself from siblings by explicitly excluding the agent's own tool calls and pointing to aseprite_pixel_map as the downstream consumer.

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 gives concrete call sequencing ('first call starts watching', 'later calls return changed pixels'), and explains peek and reset semantics. It does not explicitly name alternatives or state when not to use it, but the collaborative watch-mode context is unambiguous.

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