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

Beyond the readOnly annotation, the description discloses meaningful behavioral traits: the result already contains rendered palette and download artifacts, archive anchors must not be presented as recommended colours, and any independently chosen final palette must be passed to palette_finalize. This adds real context absent from the structured fields and does not contradict the annotations.

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 longer than average, but every sentence earns its place: it explains the differentiation, the key parameters, the output contents, a critical anti-pattern, and the required follow-up action. The 'Like palette_concept but...' opening front-loads the core purpose, and the instructions are grouped logically.

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?

Given the tool has an output schema and readOnly annotation, the description still covers the most important runtime context: what the result carries, how to present it, what not to do, and what to call next. The guidance is sufficient for an agent to select, invoke, and act correctly on this tool without additional documentation.

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%, so a baseline of 3 applies. The description adds practical meaning to allowed_archives by tying it to cultural traditions and examples, and to min_relevance by explaining it filters weak concept matches. It doesn't cover n_colours or include_neutrals, but the schema already describes those adequately, so the description provides meaningful but not exhaustive added value.

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 identifies the tool as 'Like palette_concept but with archive filtering and relevance controls', naming both the resource type and the specific differentiating behavior. It explicitly separates this tool from the sibling palette_concept and states the core benefit: 'Fixes cross-archive drift when cultural specificity matters.' This is a specific verb+resource framing that an agent can act on.

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 gives explicit when-to-use guidance ('Fixes cross-archive drift when cultural specificity matters') and names the alternative tool it builds on ('Like palette_concept'). It also provides direct parameter usage instructions for allowed_archives and min_relevance, and gives downstream workflow instructions about showing results and calling palette_finalize when selecting a final palette. This is actionable and leaves little to inference.

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