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

Annotations already establish this as a safe, idempotent, non-destructive read, so the bar is lower, but the description still adds real behavioral context: the registry setup is one-time, the install token expires in 15 minutes and only appears when the connection carries a CLI token, and the command form is constrained to @liro/<slug> never a bare URL. Those conditional-output rules are not derivable from the annotations.

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?

A single front-loaded sentence that enumerates the payload; every clause corresponds to a distinct returned artifact, so little is wasted. It is dense and list-like, but the ordering is logical and the key scoping statement comes first.

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?

With no output schema, the description carries the burden of explaining returns, and it does so thoroughly by naming each section of the response and the conditions that change it. What remains unstated — error behavior for invalid slugs, or output size for 10 components — is minor for a read-only generator.

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%, so the baseline is 3; the schema already explains mode, package_manager and slugs. The description does add one useful hint beyond the schema — sourcing installed_packages from package.json so packages are not re-suggested — but says nothing further about slugs, package_manager, or the 10-item limit.

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 opens with a concrete resource and scope ("Installation for one or more components") and enumerates exactly what the tool returns: registry setup, shadcn CLI command, agent command, missing packages, files and destinations, theme setup. It is clear this generates an install plan rather than raw component source, though it never names the sibling get_component_code it is implicitly distinguished 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?

It gives a concrete calling hint ("pass installed_packages from package.json") and explains the conditional token case, and the schema covers when to pick manual/both mode. However, there is no explicit statement of when to choose this tool over get_component or get_component_code, leaving the sibling routing to inference.

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