[duvera · risk:low] Search Wikipedia articles by keyword. Returns matching page titles, keys, and excerpts. Pass a result's key to wiki.summary for the article summary. No account required.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search terms, e.g. "zero trust architecture" or "Ada Lovelace". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that it returns titles, keys, and excerpts, and that no account is needed. Lacks details like rate limits or pagination, but for a simple search tool this is adequate given no 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?
Highly concise, single sentence with key information front-loaded. No unnecessary words.
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?
Provides sufficient context: what it does, what it returns, and how to use its output with a sibling tool. No output schema but return types are described.
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?
Input schema has 100% coverage and provides a clear description with examples. The description adds a usage hint but does not significantly extend parameter meaning 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?
Clearly states it searches Wikipedia articles by keyword and lists return types (titles, keys, excerpts). Distinguishes from sibling duvera__wiki_summary by directing to pass a key to that tool for a summary.
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?
Explicitly mentions no account required and instructs to pass result key to wiki.summary for summary. Does not explicitly discuss when to avoid using this tool, but the context is clear enough.
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.
Each tool is prefixed with its service name, and within each service, tools have distinct actions (e.g., mail_read vs. availability_find). The duvera tools cover different subdomains like dev, finance, and food with no overlap, making selection unambiguous.
All tools follow the pattern service__action_object or service__category_action, using lowercase with underscores. The order of verb and noun varies slightly (e.g., package_track vs. boardingpass_show), but the naming is highly predictable and readable.
With 52 tools, the server is large but justified as a gateway aggregating many external services. Each tool corresponds to a common task for its service, so no tool feels extraneous, though the total number is high.
The tool surface covers a wide array of services but only provides one or two basic operations per service (mostly read-only). While this suits a quick-lookup gateway, deeper workflows (e.g., creating or updating resources) are missing, leaving gaps for many use cases.
