searchNatural-language search over what Desvela has indexed: agents, MCP servers, registries — the same index as POST /search. Returns catalog entries per the ARD spec. When nothing matches, returns referrals: other ARD-conformant registries you can query the same way, instead of an empty answer.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | natural-language query, e.g. "find an MCP server for weather data" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral transparency burden. It discloses that results are catalog entries per the ARD spec and that non-matching queries return referrals to other ARD-conformant registries instead of an empty answer. This is useful, but it omits details like pagination or error behavior.
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 three sentences and every sentence adds value: it defines the search scope, specifies the return format, and explains the fallback behavior. It is front-loaded and avoids unnecessary repetition.
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 one-parameter search tool with no output schema, the description provides sufficient context: what is searched, what is returned, and what happens when nothing matches. It is complete enough for an agent to select and invoke the tool, though additional pagination or limit details would be helpful.
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 single parameter 'text' is fully described in the schema (natural-language query with an example), and schema coverage is 100%. The description does not add additional parameter-level meaning beyond what the schema already provides, so the baseline 3 applies.
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 clear action ('natural-language search') over a specific resource ('what Desvela has indexed: agents, MCP servers, registries'). It is unambiguous but does not explicitly distinguish itself from the sibling tools (preflight, watch).
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 conveys when to use the tool: to search the Desvela index and get catalog entries per the ARD spec. It also notes the fallback to referrals on no match. However, it lacks explicit guidance on when not to use it or how it compares to alternatives like preflight or watch.
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 serves a clearly distinct purpose: preflight checks declared AI-agent artifacts, crawler_block_test measures observed CDN behavior, search queries the registry index, and watch subscribes to change notifications. There is no meaningful overlap or ambiguity between them.
Tool names are readable and intuitive, but they follow mixed conventions: crawler_block_test uses a descriptive snake_case phrase, preflight is a single noun, and search/watch are imperative verbs. There is no consistent verb_noun or noun_noun pattern across the set.
Four tools is well-scoped for this registry-focused service: one for declared policy, one for observed behavior, one for discovery/search, and one for change monitoring. Each tool offers a distinct capability without redundancy or bloat.
The domain is covered end-to-end: preflight provides the declared artifacts, crawler_block_test reveals actual blocking behavior, watch monitors changes over time, and search lets users discover registry entries. The internal webhook management endpoints are appropriately handled outside the MCP surface, so there are no obvious dead ends.