Skip to main content
Glama
markdown-memory-mcp

markdown-memory-mcp

by amercans

search_notes

Find notes by meaning and keywords to recall relevant vault content; returns ranked matches with paths so you can read the full text.

Instructions

Find notes by meaning and by words. Use this to recall what the vault knows.

Args: query: What to look for, in natural language. k: How many notes to return (1-50).

Returns a list, best first, of {name, path, description, rrf, cosine, bm25}. path is relative to the vault; pass name to read_note for the full text. cosine is null when the note has no embedding yet.

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": "search_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
queryYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations present, the description does real work: it discloses that results are hybrid (RRF fusion of cosine and bm25), that ordering is best-first, and that 'cosine' can be null for unembedded notes — a non-obvious data quirk an agent could misread as failure. It omits any statement about read-only safety, auth, or result size limits, and never describes the query cost.

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

Conciseness4/5

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

Front-loaded with the purpose, then Args and Returns blocks that are easy to scan. The Returns block partially duplicates the existing output schema, but it earns its space by explaining what rrf, cosine, and bm25 mean and how name relates to read_note.

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

Completeness5/5

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

Output schema exists, so the return-shape explanation is a bonus rather than a necessity, and the description still adds the field semantics and the follow-up call to read_note. Combined with the parameter bounds it covers everything needed to invoke the tool 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 0%, so the description carries the burden and does: 'query' is specified as natural language, and 'k' is given a hard bound of 1-50 that the schema lacks entirely (it only shows a default of 5). Both parameters are covered, though 'k' lacks any guidance on choosing a value.

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

Purpose4/5

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

The first sentence gives a specific verb-plus-resource ('Find notes') and adds the retrieval mode ('by meaning and by words'), which is more precise than a bare name restatement. It also sketches the division of labor with read_note for full text, though it never explicitly frames that as 'use this instead when...'.

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

Usage Guidelines3/5

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

'Use this to recall what the vault knows' implies a recall/retrieval scenario but gives no when-not guidance and no comparison against keyword-only or structural alternatives such as backlinks. The only routing hint is the handoff to read_note, which is implicit rather than stated as a selection rule.

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