Browse an OpenViking knowledge base's directory tree with generated summaries to survey available knowledge before searching or reading specific documents.
Inspect OpenViking directory structure with generated summaries (L0/L1). Use it to survey what knowledge exists before deciding what to search or read.
| Name | Required | Description | Default |
|---|---|---|---|
| uri | No | Directory URI, defaults to the resources root. | |
| depth | No | How many levels to show. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety profile is covered. The description adds the useful detail that results come with pre-generated L0/L1 summaries, but says nothing about response volume, how deep/broad output scales, or what L0 vs L1 means.
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, zero redundancy: the capability comes first, then the usage guidance. Nothing is padded or restated from the schema.
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 two-optional-parameter read-only survey tool with full annotation coverage and no output schema, the description is nearly sufficient. The one gap is the undefined L0/L1 jargon, which is the tool's main value proposition and would help an agent judge whether the summaries suffice before calling ov_read.
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 100% with clear docs for uri (defaults to resources root) and depth (1-4 levels), so the description needs to add little. It adds nothing beyond the schema and leaves the unexplained L0/L1 notation as the only domain-specific concept, which is not tied to any parameter.
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 and resource ("Inspect OpenViking directory structure") plus the distinguishing output trait ("generated summaries (L0/L1)"). It separates itself from ov_search and ov_read by framing itself as the survey step before those actions, though it never names the siblings directly.
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?
"Use it to survey what knowledge exists before deciding what to search or read" gives a clear situational trigger and implicitly positions ov_search/ov_read as the follow-on alternatives. It stops short of explicit when-not conditions or naming the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.