Skip to main content
Glama
phygital-memory

phygital-memory

Official

search_notes

Read-only

Search personal notes by meaning and words across unlocked folders or one subfolder, returning ranked matches with snippets to find notes by topic when you don't know the path.

Instructions

Search the person's notes by meaning and words (Engram), in every unlocked folder at once, or only inside one subfolder with inside. Read only. Returns ranked results, best first: id, folder, note path, heading and a short snippet. Use it when you know what a note is about but not where it is; use list_notes to browse by path, recent_changes for the latest work. Then call open_result with an id to read one. Private notes show only as a locked line (place and section), and only open with private=true when the person asked in this chat. Says so when nothing matches.

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": {
      "question": "<question>"
    },
    "name": "search_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many results (default 8).
insideNoOnly notes inside this subfolder, like 'Projects'.
privateNoTrue only when the person asked, in this chat, for something in a folder they keep private.
questionYesWhat to look for, in plain words.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.5
    • addedInput schema / properties / inside
      Added value: +{
      +  "default": "",
      +  "description": "Only notes inside this subfolder, like 'Projects'.",
      +  "title": "Inside",
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond readOnlyHint=true, it discloses the result ordering and shape (id, folder, path, heading, snippet), the empty-result behavior ("Says so when nothing matches"), and a non-obvious privacy rule: private notes appear only as a locked line and only open when the person asked in this chat. That is genuine behavioral context not carried by annotations.

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 core action and scope, then routing, then returns, then privacy. Information-dense with almost no waste, though the opening sentence's parenthetical and the "inside" mention make it slightly denser than it needs to be.

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?

For a read-only search with a full output schema and documented params, nothing an agent needs is missing: what it searches, how to narrow it, how to read results, when private access is allowed, and what happens on no match.

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 real meaning for two params: inside restricts to a subfolder, and private carries a consent condition ("only when the person asked in this chat"). It doesn't clarify the limit cap or default, relying on the schema there.

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 ("Search the person's notes") plus the retrieval model ("by meaning and words (Engram)") and the scope (all unlocked folders, or one subfolder via inside). An agent can distinguish it from list_notes and recent_changes without opening any schema.

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?

Explicit selection rule: "Use it when you know what a note is about but not where it is", with named alternatives and their conditions (list_notes to browse by path, recent_changes for latest work). It also names the mandatory follow-up (open_result with an id) and the precondition for private=true.

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