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

Annotations already disclose readOnly, idempotent, and non-destructive behavior, so the description does not need to restate it. It adds the kebab-case naming convention and lists what the result contains, but that list is largely return-value information which the output schema already covers. No auth, error, or rate-limit behavior is described.

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 sentences: the first front-loads what the tool returns and the second is a crisp, actionable instruction. There is no redundant text or tautology, and both sentences earn their place.

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 single-parameter, read-only retrieval with an output schema and full annotations, the description is adequate. It explains the resource returned and the valid source of the parameter, though it stops short of describing behavior with invalid or nonexistent names.

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?

The schema already documents 'name' with examples, so the baseline is 3. The description adds extra meaning by requiring the kebab-case format and directing the agent to use names from list_components or search_components, which provides provenance and format guidance beyond the schema.

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 states a specific retrieval operation (get the markdown docs page for a component) and enumerates the returned resource pieces: props JSON, CSS snippet, React example, classes, and aliases. This distinguishes it from siblings like list_components, search_components, and get_guide.

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?

The description tells the agent to pass the kebab-case name from list_components or search_components, which establishes a clear input source and implicitly says when to use this tool (once a specific component is known). It does not explicitly explain when to choose it over get_guide, get_install, or get_tokens, but the resource type is clear enough.

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