Finds the sections of the reference that best answer a question or a few words, such as 'sortable table', 'dark mode' or 'error message on a field'. Each result names its page and section, for get_page.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| version | No | The @nuvui/react version in the project's package.json, such as 0.6.2 or ^0.6.0, for the docs of that release. Leave it out for the latest release. |
Changes observed during successful MCP inspections.
Input schema / properties / versionAdded value: +{
+ "description": "The @nuvui/react version in the project's package.json, such as 0.6.2 or ^0.6.0, for the docs of that release. Leave it out for the latest release.",
+ "maxLength": 40,
+ "minLength": 1,
+ "pattern": "^(?:\\^|~|>=|=)?v?\\d+(?:\\.(?:\\d+|x|\\*)){0,2}(?:-[0-9A-Za-z.-]+)?$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond them: results are section-level, each labeled with page and section identifiers, and are intended as input to another tool. It omits ranking/return-volume behavior and the default result limit.
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, front-loaded with the action and scope; the example queries are short and earn their place by showing query granularity, and the get_page follow-up closes the loop without filler.
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 usefully explains the shape of a result (page + section). Together with the schema's version guidance, an agent has enough to call this correctly; only limit/pagination behavior and the absence of any exclusivity guidance leave gaps.
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 only 33% — only 'version' is documented in the schema, while 'query' and 'limit' are bare. The description partly compensates by characterizing 'query' as a question or a few words, but says nothing about 'limit' (default 8, max 20), which is real information an agent needs to control result size.
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 (finds) and resource (sections of the reference that answer a question), and immediately distinguishes itself from the retrieval sibling by noting results feed get_page. An agent can tell it apart from get_page, list_guides, etc. without opening a schema.
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 gives concrete example queries ('sortable table', 'dark mode') that clarify the intended usage shape, and states the follow-up (results name page/section 'for get_page'), implying a search-then-fetch workflow. It never states when NOT to use it or when to call get_page directly, so it stops short of explicit routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.