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

Annotations already declare readOnlyHint=true, and the description adds substantial behavior beyond that: the result payload carries the rendered palette plus PNG/PDF/ASE/JSON/CSS downloads, the agent must surface those to the customer, and a hard guardrail forbids presenting archive anchor colours as recommendations. No contradiction with readOnlyHint exists.

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?

Four sentences, each carrying distinct content: what it does, what the result contains and how to present it, a one-line guardrail, and the follow-up routing. The core purpose is front-loaded in the first sentence and no sentence is wasted, though the density is moderately high.

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?

With an output schema present and readOnlyHint in annotations, the description need not restate return structure or safety. It nonetheless covers the payload contents, the presentation duty, a correctness guardrail, and the follow-up workflow, leaving nothing an agent needs to call the tool and act on the result correctly.

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 the baseline is 3 even without parameter detail in the description. The description adds only marginal parameter meaning — 'for the stated use case' ties use_case to the verdict — while palette_a, palette_b, and markets semantics are already fully documented in the schema.

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 — 'deep perceptual, cultural, and commercial comparison between two palettes' — and enumerates concrete outputs (timelessness scores, commercial strength, cultural depth, emotional difference, winner verdict). This specificity pins the tool down and distinguishes it from adjacent siblings like colour_compare or palette_verdict, whose purpose is not anchored to this multi-dimensional head-to-head verdict.

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 establishes clear context ('for the stated use case') and gives explicit conditional routing to a sibling: call palette_finalize if you choose a final palette of your own from the evidence. It stops short of stating when not to use this tool versus its direct comparison siblings (colour_compare, palette_verdict), so it earns a 4 rather than a 5.

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