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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new context: it is a preview API that may change without a version bump, it requires the products:read scope, and it excludes recipe/mix data. These are traits an agent cannot get from the annotations or schema.

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?

Three compact clauses with the capability first, then the filter constraint, then permission/preview caveats — well front-loaded and free of padding. It is terse to the point of being telegraphic, which slightly hurts readability but not efficiency.

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 no output schema, the description does list the returned content (catalog, barcodes, pack balances), which is helpful. But for a 6-parameter tool with 17% schema coverage, it omits the meaning of the required locationId and the limit/pagination interplay, so it is not fully sufficient to call the tool confidently.

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 only 17% (only 'after' is documented), so the description must compensate. It does clarify the mutual exclusivity of rangeId, ean and articleNumber, which the schema does not encode, but leaves locationId (required), limit, and the semantics of the colour-bar item fields unexplained.

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 names the payload ('Shade/item catalog, barcodes and pack balances') and the title supplies the verb ('List colour bar items'), but the description itself never states the action or resource explicitly and reads like a category label. An agent must combine name + title + description to infer that this lists colour bar items for a location.

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?

'Choose at most one of rangeId, ean or articleNumber' gives a hard usage constraint, and 'no recipe or mix data' rules out one expected use. However, there is no guidance on when to pick this over sibling tools such as cliento_get_colour_bar_item or cliento_list_colour_bar_ranges, so alternative selection is left to inference.

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