Skip to main content
Glama
shaqmughal

seekstone

by shaqmughal
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

search

Read-only

Find ranked excerpts across an Obsidian vault by keyword, tag, folder, fuzzy/prefix match, or semantic meaning, returning snippets instead of full notes to save context.

Instructions

Full-text search across the vault. Returns ranked excerpts (~120 chars, tunable) — not full notes — to minimise context usage. Supports fuzzy matching and prefix search; with SEEKSTONE_SEMANTIC=1, mode "semantic"/"hybrid" searches by meaning via a local embedding model.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagNoRestrict to notes with this tag. # optional, case-insensitive; nested child tags match ("project" matches project/alpha).
modeNolexical = keyword search (default). semantic = meaning-based search (requires SEEKSTONE_SEMANTIC=1). hybrid = exact-title lookups go lexical, everything else semantic.
limitNoMax results (1–50, default 10).
queryYesSearch query.
folderNoRestrict to a vault-relative folder prefix.
excerptLengthNoMax characters of match context per hit (20–2000, default 120).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.26
    • changedInput schema / properties / tag / description
      Previous value: -"Restrict to notes with this tag."New value: +"Restrict to notes with this tag. # optional, case-insensitive; nested child tags match (\"project\" matches project/alpha)."
  2. Changed1 schema field changedv0.3.19
    • addedInput schema / properties / excerptLength
      Added value: +{
+  "description": "Max characters of match context per hit (20–2000, default 120).",
+  "type": "number"
+}
  3. Changed1 schema field changedv0.3.18
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "lexical = keyword search (default). semantic = meaning-based search (requires SEEKSTONE_SEMANTIC=1). hybrid = exact-title lookups go lexical, everything else semantic.",
+  "enum": [
+    "lexical",
+    "semantic",
+    "hybrid"
+  ],
+  "type": "string"
+}
  4. First observedv0.3.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral context beyond them — excerpt size (~120 chars, tunable), fuzzy and prefix matching, and the environment-variable gate on semantic mode. It stops short of describing ranking behavior or whether results are paginated.

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?

Three dense sentences, front-loaded with the core verb and result shape, then the matching capabilities, then the conditional semantic mode. No filler and nothing repeated from the schema.

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?

With no output schema, the description carries the return-value burden and does so well (ranked excerpts, approximate length, tunability), and it covers all six parameters indirectly. Minor gaps remain around result ordering/ranking guarantees, but an agent has enough to invoke it correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: excerptLength is framed as the tunable knob that controls context cost, and semantic/hybrid mode is tied to a required environment flag. These are genuine additions rather than restatements.

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?

States a specific verb and resource ('Full-text search across the vault') and immediately characterizes the result type ('ranked excerpts — not full notes'), which distinguishes it from content-returning siblings like read_notes, read_note and query_notes without opening their schemas.

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

Usage Guidelines4/5

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

The 'not full notes — to minimise context usage' framing implies when to prefer this over read_notes, and the semantic/hybrid modes come with an explicit precondition (SEEKSTONE_SEMANTIC=1). However, no sibling tool is named directly and no explicit when-not guidance is given, so the agent must infer the routing.

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