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

The readOnlyHint annotation already signals a safe, non-mutating operation. The description adds meaningful behavior beyond this: it promises a 'clean, text-free' output, specifies the return format ('URL to the PNG'), and highlights a key differentiator of the gradient layout ('true smooth LCh-interpolated gradient with no hard edges'). These details help the agent set expectations and choose layouts appropriately, though it does not cover every possible edge case (e.g., size limits or error handling).

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?

Three sentences, each earning its place. The first states the core action and output, the second gives the two primary use cases, and the third enumerates supported layouts with a key differentiator. No filler or redundant phrasing. Information density is high but still readable.

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?

Despite having 5 parameters and a moderately complex set of layouts, the description is complete for an agent to invoke the tool correctly. It covers the purpose, return type, primary use cases, and layout-specific behavior. The existence of an output schema and fully-described input schema reduces the need for additional detail, and the description fills the remaining gaps (like the gradient's subtlety and the weights' role).

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 input schema provides 100% coverage of parameters, so the baseline is 3. The description adds value by explaining that 'photo-proportional weights' come from palette extraction and are used specifically for the photo layout, and it stresses that the gradient layout is a smooth perceptual blend unlike the others. These semantic hints go beyond the schema's terse property descriptions, clarifying how parameters interplay.

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 opens with a specific verb and object: 'Generate a clean, text-free PNG swatch image from hex colours.' It immediately states the deliverable (a URL to the PNG) and explicitly names two distinct use cases (Midjourney --sref style references and design mood boards). This clearly differentiates the tool from siblings like palette_gradient or palette_export, as it focuses on swatch image generation for style references.

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 provides explicit 'when to use' guidance: 'Use for Midjourney --sref style references or design mood boards.' It also gives a nuanced recommendation for the gradient layout: 'best for mood/atmosphere/colour-grade references rather than literal composition.' While it does not explicitly name alternative sibling tools, the use cases and layout-specific guidance are sufficient to steer an agent. The absence of explicit exclusions (e.g., 'do not use for...') keeps it from a 5.

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