Generate a colorblind-safe palette

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

With no annotations, the description carries the full burden and does real work: it discloses the seeding strategy (Okabe-Ito), the behavior above eight colors ('safely extended'), and a hard output invariant ('Never returns an unsafe color'). It still omits determinism (is the same count reproducible across calls?) and the ordering/format of the returned colors.

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 sentences, each earning its place: the output contract first, the implementation guarantee second, the trigger third. No restatement of the title or 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 single-parameter, annotation-free tool with no output schema, the description covers the guarantee, the seed basis, and the call trigger, which is enough to invoke it correctly. The remaining gap is the return shape (array of hex strings) and reproducibility, which the agent must infer.

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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema's bare '1..24' range by explaining what happens to the count above eight colors. It still does not clarify behavior at the 24 cap or whether counts map to a fixed ordering.

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+resource ('Return N colorblind-safe hex colors') and immediately defines the guarantee that distinguishes it: distinctness under protanopia, deuteranopia and tritanopia. The generative verb separates it from the sibling verbs (checkContrast, checkPalette, fixPalette), so an agent can route without opening any schema.

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?

Gives an explicit trigger: 'Use when asked for accessible / colorblind-safe / colorblind-friendly colors for a chart, plot, map or UI.' That covers the when-to-use side well, but it never states when NOT to use it or names the sibling to prefer for related tasks (e.g., verify an existing palette with checkPalette / fixPalette).

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