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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: it never installs anything, official upstream items require compatibility review and are not runtime verified, and it returns ready-to-use JS with correct imports. The note about 'bounded dependency/CSS/provenance information' also hints at inspect's output scope.

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?

The description is poorly front-loaded: it opens with action-level details before stating the tool's main purpose ('Get shadcn/ui component code pre-adapted...'), and the component list is repeated verbatim from the schema. Several sentences (e.g., 'Default action local retrieves...') are awkward and could be tightened.

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 read-only tool with seven fully described parameters and no output schema, the description covers the actions, a key caveat about upstream items, and the return format at a high level. It still leaves gaps around pagination behavior for search, the exact shape of inspect results, and error handling, which an agent might need.

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 every parameter is already documented in the input schema, including the component list, action enum values, registry, and tailwindVersion. The description restates the component list and action meanings but adds no format or constraint details beyond the schema; baseline 3 is warranted.

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 three concrete actions (local retrieves adapted components, search discovers the official catalogue, inspect reads source/provenance) and states the overall goal of getting pre-adapted shadcn/ui code for Sandpack. It distinguishes the actions internally but does not clearly differentiate the tool from siblings like build_app.

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 directive ('Use this instead of building complex UI primitives from scratch') and implies when each action applies via their definitions. However, there are no explicit exclusions, no guidance against using build_app for the same purpose, and no prerequisites stated beyond the upstream compatibility caveat.

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