searchSearch this site's content. Returns matching documents (id, title, url); pass an id to fetch for the full text.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query |
| Name | Required | Description | Default |
|---|---|---|---|
| results | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds context beyond those: it reports the output shape (id, title, url), indicates that this is a metadata-level search rather than full-text retrieval, and identifies the follow-up tool by name. The 'this site's content' phrasing also clarifies 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?
Two focused sentences convey the action, result format, and the intended follow-up tool. There is no redundancy or filler, and the most important information is front-loaded.
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 search tool with an output schema and informative annotations, the description is nearly complete. The main remaining gap is the unaddressed relationship with the similarly named `search_articles` sibling, which could affect tool selection.
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 input schema covers the only parameter, `query`, with 'Search query', so schema description coverage is 100%. The description adds no new meaning about query formatting, syntax, or matching behavior; it relies on the schema, which is sufficient.
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 clearly states the action ('Search'), the resource ('this site's content'), and the return shape ('matching documents (id, title, url)'). It distinguishes itself from `fetch` by noting that full-text retrieval is delegated to that sibling, but it does not explicitly differentiate itself from the overlapping `search_articles` sibling.
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 a clear usage path: use search to get document metadata, then pass an id to `fetch` for full text. However, it provides no guidance on when to use `search` versus `search_articles`, `get_article`, `list_recent_articles`, or `popular_content`, so the selection decision among siblings is incomplete.
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.
The set has clear overlaps: search and search_articles both perform keyword search, while fetch and get_article both retrieve full text using different identifiers. An agent could easily select the wrong tool, especially since the descriptions do not clarify when one search path is preferred over the other.
Tool names are mostly verb-led but not uniform: fetch and search are bare verbs, get_article and search_articles use verb+object, list_recent_articles is verb+adjective+noun, and popular_content is a noun phrase. The naming is readable but lacks a consistent convention.
Six tools is a reasonable size for a content gateway, but two pairs of near-duplicates reduce the effective surface and leave some redundancy. The count itself is not excessive, but the same functionality could be delivered with fewer, more distinct tools.
Core content-retrieval workflows are covered: searching, fetching full articles, viewing recent articles, and accessing popular content. Minor gaps exist, such as category/author browsing or pagination, but they are not critical dead ends for the apparent purpose.