lint

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

With no annotations at all, the description carries the full burden. It discloses the diagnostic categories and that results carry coordinates, which is useful, but never states that it is a read-only/no-mutation operation, what the return payload looks like, or how it behaves on a path that doesn't resolve to a sprite.

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 dense sentences with no filler; the output (coordinates plus findings) is front-loaded ahead of the scoping advice. The opening clause "Find what is easy to miss" is slightly rhetorical, but it earns its place by framing the tool.

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 a three-parameter tool with no annotations and no output schema, the description covers the detection categories and the layer/frame choice but leaves the return shape, the meaning of `path`, and the read-only nature unspecified. Adequate to invoke, incomplete for confident use.

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 and it only partly does: the layer-versus-frame relationship is explained in real terms (a layer lints one object, the flattened frame lints everything composited). The required `path` parameter and the numeric frame index (default 1) are left entirely unexplained by both schema and description.

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 concrete verb-and-resource: it finds pixel-art anomalies and reports them with coordinates, then enumerates the specific checks (orphan pixels, lone pixels, detached parts, colour count, darkest colour share, out-of-canvas pixels). An agent knows exactly what it gets back conceptually. It does not differentiate itself from close siblings such as find_glitches or check_identity, so it stops short of a 5.

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?

"Use a layer for one object; the flattened frame touches everything else" tells the agent how to scope the call, which is genuine guidance. But there is no when-to-use-versus-siblings statement, no exclusion, and no prerequisites, so usage is only implied.

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