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

With readOnlyHint=true already covering the safety profile, the description adds substantial behavioral context: hay_contrast snaps to Hay's nearest named hue, returns covered:false when the input is near a tertiary region, and never invents a partner. It also discloses that the result already contains downloads and instructs the agent not to present archive anchors as recommendations. This goes far beyond the annotation.

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 dense and front-loaded with the core purpose, and every clause carries relevant behavioral or usage information. It is longer than a minimal description, but the complexity of the hay_contrast mode and the downstream finalize instruction warrant the length. Some Hay context repeats what the input schema already says, which keeps it from a perfect 5.

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 complexity of the tool, the output schema presence, and the read-only annotation, the description covers everything an agent needs: what the tool returns, when it fails, what to show the customer, what not to present, and when to route to palette_finalize. No critical operational gap remains.

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 the baseline is 3. The description goes further by explaining the behavioral semantics of the hay_contrast parameter value: nearest-hue snapping, tertiary handling, and covered:false. It also clarifies how harmony_types values behave differently from one another. It doesn't add much about the hex parameter beyond the schema, but the hay_contrast detail justifies the score.

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 uses a specific verb, 'Return', names the resource ('colour harmonies'), and enumerates the harmony types, so an agent can tell what the tool does. It also meaningfully distinguishes the hay_contrast mode from the fixed-angle types within the tool. However, it does not explicitly differentiate this tool from similar siblings like colour_relationships or palette_generate, so it stops short of 5.

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 clear when-to-use guidance: it explains the hay_contrast option, says when the tool returns covered:false, and tells the agent to show the rendered palette assets to the customer. It also provides an explicit conditional for a sibling action: if the agent chooses its own final palette, call palette_finalize once with those exact colours.

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