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

Annotations only say this is a non-read, non-destructive write; the description goes well beyond by disclosing the null-clearing behavior, the propagation rules to other artifact types, the constraint that the id must be a design system you can read, and the exact return shape. That is the kind of downstream-effect detail a mutation tool needs.

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: operation first, side effects second, contract third. No filler, and the null-clear case is stated up front rather than buried.

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?

A single-parameter mutation with no output schema, yet the description covers mutation semantics, null handling, propagation to dependent artifact types, validation constraint, and return shape. Nothing material is left for the agent to guess.

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 0%, so the description carries the burden and does: system is a design system id you can read, or null to clear. It also implicitly documents the required-but-nullable typing by pairing the two accepted values with their meanings.

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 and resource ("Set ... your default design system") plus the null-clearing variant in the same clause. It is clearly distinguishable from siblings like system_install (install into a scope) and systems_list (enumerate), since it explicitly concerns the user's default.

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 concrete downstream effects: new slides, design and dashboard artifacts inherit it automatically, while html artifacts only receive it when system is passed to publish_html. That is a real when-it-applies / when-it-doesn't distinction, though it never names system_install as the alternative for one-off installs.

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