apply_filter

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is largely covered and the description is consistent with it. The description adds the supported-filter enumeration, which is real behavioral content, but says nothing about live-vs-batch effects, the save-writeback behavior, or whether edits are undoable.

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 tightly packed sentences with the core action and filter list front-loaded and the parameter examples second. Dense but no filler; a small readability cost from cramming all examples into one sentence.

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 an 8-parameter, nested-object mutation tool with no output schema, the description covers only the filter/params axis; the frame, layer, sprite, backend, and save parameters are left entirely to the schema. It is adequate to invoke the tool, but the batch-vs-live behavior and write-back semantics an agent needs for correct use go unmentioned.

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 'params' property in the schema is an open object with no documented shape, so the description's concrete examples (Outline {color, place, matrix}; HueSaturation {hue, saturation, lightness, alpha}; BrightnessContrast {brightness, contrast}) carry information the schema cannot. It stops short of covering ColorCurve, ConvolutionMatrix, Despeckle, InvertColor, and ReplaceColor, so the gain is partial.

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 ('Applies') and resource ('image filter command') plus the exact scope ('active cel(s) or selection'), and enumerates the eight supported filters, which makes the tool easy to identify. It does not, however, contrast itself with neighboring mutators like replace_color or draw_pixels, so sibling differentiation is left to the reader.

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 implied rather than stated: the agent infers this is the tool for the listed filters, and the pointer that 'Params follow list_commands' is a useful routing hint to a sibling. There is no explicit when-to-use/when-not guidance or description of prerequisites (active sprite, connected live session, etc.).

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