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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the return value is a command string plus a config snippet, and Pro items require an environment variable before use.

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?

Two tightly written sentences with no filler; what the tool returns comes first and the prerequisite follows. Every clause carries distinct information.

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 simple one-parameter read tool with no output schema, the description covers both the primary return (a CLI command) and the secondary return (the registries snippet) plus the token prerequisite. Nothing an agent needs to call it correctly is missing.

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 slugs parameter is documented with an example in the schema, so the baseline is 3. The phrase 'every listed item' loosely maps to slugs but adds no batching, ordering, or error semantics beyond the schema's 1-30 item bounds.

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 names a concrete output: a single shadcn CLI command that installs every listed item, plus a components.json registries snippet. That is a specific verb-plus-resource, and it is clearly different from get_item or get_source, though it never names a sibling to route away from.

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?

Usage is only implied by the wording 'installs every listed item into the project'; there is no explicit statement of when to pick this over get_item or get_source and no exclusions. It does surface one real prerequisite, that Pro items need PIXILUI_TOKEN, which keeps it above a bare minimum.

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