Paint: Image filter

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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds real value beyond that by noting that 'undo works the same for every drawing tool', implying the operation is reversible, which is exactly the behavioral context an agent needs for a mutation tool.

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?

Front-loads the filter list then moves to per-parameter semantics and targeting context. The long enum enumeration is necessary but makes it dense; otherwise little waste.

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 9-parameter, nested-schema mutation tool with no output schema, the description covers the important semantics (filter list, amount units, area, level) and the canvas/layer targeting model. The unexplained `seed` parameter is the one notable 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 only 56%, so the description must compensate. It does so for the undocumented `amount` (units vary per filter) and `level` (posterize/dither levels) parameters, but leaves `seed` unexplained in 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 specific verb (filters) and resource (a layer) and enumerates all 18 filter modes by name, making it unmistakably the image-filter tool rather than a sibling like paint_transform or paint_pixels. The mention of paint_canvas as the canvas source anchors it in the family.

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?

The description tells the agent how to target the canvas and layer, and notes that layers/filters/undo behave the same across drawing tools, but gives no explicit when-to-use-vs-alternative or when-not guidance. Usage is implied rather than stated.

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