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

Beyond the readOnlyHint annotation, the description reveals important behaviors: hay_contrast snaps to Hay's nearest named hue, returns covered:false with no invented partner for tertiary regions, and the result already includes rendered palette downloads. It also warns against presenting derived archive anchors as recommendations. This significantly exceeds annotation-level transparency.

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?

Every sentence earns its place: the first defines the core function, the second explains the special case, the third clarifies output, the fourth warns about a common misuse, and the fifth routes to the correct follow-up tool. There is no fluff or repetition, and the most important information is front-loaded.

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's complexity (a special historical contrast mode with edge cases) and the presence of an output schema, the description covers everything an agent needs: available harmony types, hay_contrast's unique behavior, output deliverables, customer presentation, and the exact condition for calling palette_finalize. No critical usage detail is missing.

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 baseline is 3. The description adds meaningful context for harmony_types, especially hay_contrast's snapping behavior and its edge-case covered:false result. It does not add new semantics for the hex parameter, but the extra behavioral detail for the special harmony type justifies a score above baseline.

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 resource: 'Return complementary, triadic, analogous, and split-complementary harmonies matched to named archive colours.' It clearly distinguishes this tool from siblings by naming the exact harmony types and highlighting the unique hay_contrast mode. The reference to palette_finalize as a downstream step further clarifies its role in the workflow.

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 explicitly differentiates hay_contrast from fixed-angle types, explaining when it snaps and when it returns covered:false. It also gives direct routing guidance: 'If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once...' and instructs the agent to show the downloaded result to the customer. This is actionable, unambiguous usage guidance.

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