ICC profile

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the output is returned as a base64 embedded resource, the profile flavor depends on the space type and interoperates with specific ecosystems (lcms, ArgyllCMS, ImageMagick, Photoshop), and class/pcs/bytes describe the result.

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 sentences, front-loaded with the core outcome (a space rendered as an ICC v2 profile) followed by the format-selection rule and return shape. The ecosystem name-drops (Photoshop, lcms, ArgyllCMS) are dense but each justifies the variant it belongs to.

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?

An output schema exists, so return values need not be explained, yet the description still identifies the class/pcs/bytes fields it returns. Combined with the format-selection rule and the spaces-tool pointer for valid names, an agent has enough to call this 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?

Schema description coverage is 100%, so the baseline is 3; both `name` (with the sibling pointer to spaces) and `grid` (CLUT-only, lattice points, smaller file with fewer) are already documented in the schema. The description's CLUT-vs-matrix rule contextualizes when `grid` applies, but adds no syntax or format detail beyond the schema.

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 states the artifact produced: an ICC v2 profile (.icc) for a given color space, and explains the two representations it can take. The generating verb is implied rather than stated ('One space as an ICC v2 profile'), and it does not name a sibling export tool (cube, shader, css), so differentiation is only partial.

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 the conditional logic for which profile type results (matrix+tone curve for RGB working spaces, CLUT on Lab PCS otherwise), which is genuine guidance about outcomes. However, it never says when an agent should choose icc over the sibling export tools (cube, css, shader, code), leaving the selection decision implicit.

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