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

Annotations only declare readOnlyHint=true, and the description adds substantial context beyond that: how pairs are judged (hue relationship and lightness contrast), that each item is named from its nearest archive record with that record's evidence grade and source, the epistemic caveat that no historical precedent is claimed, and that the result already carries a rendered palette with PNG/PDF/ASE/JSON/CSS downloads. It also gives a critical non-obvious constraint ('Never present the archive anchors a colour was derived from as the colours you are recommending') plus the palette_finalize handoff.

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?

Purpose is front-loaded in the first sentence and the reader progressively gets judging method, output contents, caveats, and handoff. It is dense and runs long with several directives packed into the back half, but every sentence carries distinct information rather than filler.

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?

For a stylist-facing analysis tool, the description supplies everything an agent needs: accepted input shape, what the verdict returns, the archive-provenance caveat, the download bundle, and the explicit condition for the follow-up palette_finalize call. With an output schema present, return formatting is legitimately left to the schema.

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 schema already documents items/hex/label, ask, and occasion, including the exact label vocabulary. The description's examples and label list largely restate that; the marginal addition (verdict outputs derived from items) is real but thin, so the high-coverage baseline of 3 applies.

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?

States a specific verb and resource: submit outfit items as hex+label and receive a verdict on what works, clashes, is missing, and what to add. It also carves out a distinct niche against the archive/search family ('The archive documents single colours, not outfits'), so an agent can tell it apart from colour_combination or historical_colour_query without opening schemas. It stops short of naming a specific alternative sibling, which keeps it at 4 rather than 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?

Two concrete worked examples ('navy dress + tan bag — what shoes?', 'Does this burgundy coat work with olive trousers?') establish when to reach for it, and it explicitly routes a downstream case ('If you go on to choose a final palette OF YOUR OWN... call palette_finalize'). What is missing is any explicit when-not / use-instead routing for the closely-related siblings.

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