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

With no annotations, the description carries the full burden and does so well: merge-vs-replace semantics ('Sections you send MERGE... replace:true swaps them'), the immediate side effect on :root, the write path (site first, then copied to the project), and the meaning of a partial sync result. This is unusually rich behavioral disclosure.

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?

Front-loaded with purpose and merge semantics, with rules and prerequisites at the end. It is dense and packs parenthetical asides and backticked field references, making sentences long, but nearly every clause carries actionable 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 zero-annotation mutation tool with nested objects, the description covers preconditions, merge/replace behavior, side effects, and result interpretation, and it points to the skill doc for the deep contract. An output schema exists, so return-value detail is correctly deferred.

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 schema already documents colors, buttons, replace (including merge vs wholesale), and typography in detail. The prose mostly restates that; it does add the merge default behavior framing and the 'tokens go live at once' effect, but no syntax or format detail beyond the schema, so 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 uses a specific verb (Update) on a specific resource (the design system this site paints with) and enumerates the covered sections: colours (16 canonical roles), typography, and button variants. It is immediately distinguishable from the read sibling (get-design-system) and create-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?

It states a prerequisite ('get-design-system first'), a when-not condition ('Refused when the site has none selected'), and a required pre-read ('get-skill-doc {id:"design-system-contract"} — read it before the first call'). It even clarifies that a `synced:false` result 'is not a failure to retry', which is exactly the kind of guidance an agent needs.

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