util_cbas

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the mutation/idempotency profile is covered structurally. The description adds only the visual outcome (salmon carbons) and omits meaningful behavior: that applying this overwrites existing atom colors, whether it is reversible, and what the rest of the element palette looks like.

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?

It is a single short line with no wasted preamble, which is good, but the parenthetical merely expands the abbreviated name rather than front-loading the effect. Shortness here reflects under-specification more than discipline.

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?

An output schema exists and the tool is simple, so the description does not need to explain return values. However, for a palette tool the description should at least indicate the element-to-color mapping and that the selection defaults to the whole object, which it does not.

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% and the single 'selection' parameter is documented in the schema as 'What to recolour. Defaults to everything.' The description contributes nothing beyond that, so the baseline 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?

The description does say it recolors atoms with a specific scheme (salmon carbons), but the tool name 'util_cbas' is an opaque abbreviation and the parenthetical '(Color By Atom, Salmon)' is essentially a decoding of the name rather than a statement of effect. It never distinguishes this from the many sibling schemes (util_cbam, util_cbay, util_cbab, util_cbao, util_chainbow, util_color_by_element), so the agent still has to infer that 'cbas' means the salmon variant of a family.

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?

There is no when-to-use or when-not-to-use guidance at all. With roughly eight sibling color-by-atom schemes plus generic color tools (color, util_color_by_element, spectrum) available, nothing tells the agent which situation calls for salmon carbons versus another palette.

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