Retrieve relevant passages from connected Obsidian vaults or document folders using vector similarity. Filter by source, path prefix, and score threshold to ground answers with cited source paths.
Raw vector retrieval without the LLM.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| top_k | No | ||
| source | No | ||
| path_prefix | No | ||
| score_threshold | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description must carry full behavioral context. It only states that retrieval is raw and bypasses the LLM; it does not disclose return format, ranking behavior, side effects (or lack thereof), scoring semantics, or any edge cases. This is a minimal behavioral disclosure for a tool with no annotation coverage.
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 a single front-loaded sentence with no filler, and the key differentiator ('without the LLM') is present. It is concise, though its brevity sacrifices content, keeping it from a top score.
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, five parameters, and no annotations, the description is too sparse to be complete. It does not explain what results look like, how score_threshold behaves, how source/path_prefix filtering works, or what distinguishes this from the sibling 'query' tool with any specificity.
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 0%, and the description adds no information about the five parameters—text, top_k, source, path_prefix, or score_threshold. 'Raw vector retrieval without the LLM' does not compensate for undocumented parameters, leaving an agent to guess semantics from parameter names alone.
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 uses a specific verb ('retrieval') and resource ('vector') and immediately distinguishes it from the LLM-based alternative with 'without the LLM.' This lets an agent differentiate it from sibling tools like 'query' at a glance.
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 phrase 'without the LLM' implies this tool is for raw retrieval when LLM processing is not desired, but it never explicitly states when to choose this over 'index' or 'query,' nor does it mention any exclusions or prerequisites. The usage guidance is only inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.