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

Annotations only carry readOnlyHint/openWorldHint, so the description usefully adds that the output is a URL plus a compact summary and that the URL is the actual deliverable that opens a live system. It does not discuss auth, latency, or state persistence (whether the 'modify' via url param is server-side or hash-encoded), leaving a small gap.

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 tight sentences, front-loaded with what is generated and what is returned, then the agent instruction. No filler, and the alternative tool is mentioned last where it does not dilute the primary purpose.

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 13-param tool with no output schema, the description covers the essential missing piece (what is returned: URL + summary) and defers per-field semantics to the 85%-covered schema. It stops short of explaining interactions between params (e.g. brandPin with brandInvert), so it is strong but not exhaustive.

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 85%, so the schema already documents params like mode, accents, chromaScale and the pin/invert flags in depth. The description adds almost no parameter-level detail beyond restating that scales derive from the brand color, so the baseline 3 is appropriate.

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 (generate) and resource (OKLCH color palette) with concrete scope: 18-step scales, semantic tokens, light+dark modes. It also names its outcome artifact (a shareable standby.design URL), which lets an agent distinguish it from siblings like export_design_system.

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?

Explicitly routes the agent: 'Use export_design_system for full CSS/Tailwind output' names the alternative and the condition selecting it, and 'Always give that URL to the user' prescribes post-invocation behavior. This is exactly the when/when-not guidance the dimension asks for.

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