Palette

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

Annotations indicate readOnlyHint=false and destructiveHint=false, meaning the tool may modify state but is not destructive. The description uses verbs like 'generate', 'pick', 'extract', and 'return', which suggest read operations, but it doesn't clarify whether the tool modifies the document (e.g., by creating a palette layer) or simply returns data. This omission leaves ambiguity about side effects.

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?

The description is two sentences, front-loaded with the overall purpose, followed by a bullet-like enumeration of actions. Every word serves a purpose with no fluff or redundancy.

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?

The description covers the core functionality and return types for each action, but lacks mention of prerequisites (e.g., an active document for 'from-image') or error conditions. Given the tool's moderate complexity and lack of output schema, the description is nearly complete but has minor gaps.

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 100% with descriptions for all parameters. The description adds valuable context beyond the schema, such as noting that baseColor is 'required for generate', harmony can be omitted for all types, and variant can be omitted for random. This significantly enhances parameter understanding.

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 tool's purpose: 'Generate and work with color palettes.' It enumerates four specific actions with concise explanations, distinguishing the tool from siblings like ps_color by its focus on palette generation and extraction.

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 clear context for each action (generate, from-mood, from-image, from-brand), guiding when to use each based on user intent. However, it lacks explicit exclusionary guidance or direct comparison to sibling tools, which would make it more robust.

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