Skip to main content
Glama
Sign In
Obsidian Everywhere

Obsidian Everywhere

by junnnnnw00
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Semantic Search

semantic_search
Read-onlyIdempotent

Find Obsidian notes by semantic meaning, even when exact keywords don't match. Query in natural language to retrieve relevant vault notes.

Instructions

Optional meaning-based search via local multilingual-e5-small embeddings. Requires OBSIDIAN_EVERYWHERE_ENABLE_SEMANTIC=true because the model can exceed 500 MiB RSS; the default low-memory mode keeps graph, FTS, attachment search, and Jaccard related-note search available without loading it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results (default 10).
queryYesFree-text search query.
folderNoOptional vault-relative folder scope.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds useful behavioral context about the model loading memory requirement (500 MiB RSS) and the env var, which goes beyond the structured annotations. It does not contradict any annotation, though it omits any explicit return behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is just two sentences, front-loaded with the core purpose, and every clause adds necessary context (enable condition, memory impact, and alternatives). No filler or redundant phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (3 params, readOnly annotations), the description covers the critical boundary conditions (env var, memory impact) and differentiations from siblings. It does not mention what the output looks like, but since output schema is absent, this is a minor gap; overall it is complete enough for an agent to understand the tool's purpose and surprises.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all three parameters (query, limit, folder) with full coverage (100%). The description does not add any extra semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Optional meaning-based search via local multilingual-e5-small embeddings' and clearly distinguishes it from FTS and other search methods. The verb and resource are explicit, and the alternative methods (FTS, attachment search, Jaccard related-note) are named, making the tool's niche unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when the tool is unavailable (unless the environment variable is set) and suggests that alternatives like FTS and Jaccard search remain usable without loading the model. This gives explicit context for when to choose this tool vs siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools