Skip to main content
Glama

notes_save

Save a fact or note into the agent's memory. Use scope to choose visibility: 'workspace' = visible to every agent in this workspace (use for shared facts, project conventions); 'agent' = private to this agent (use for personal working notes); 'thread' = scoped to one conversation (use for thread-specific reminders); 'person' = scoped to one contact (use for per-contact context). If a note with the same key+scope exists it will be updated. Do NOT use this tool for behavioral rules or corrections — use feedback.save for those.

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": {
      "key": "<key>",
      "value": "<value>",
      "scope": "<scope>"
    },
    "name": "notes_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesShort identifier for this note (must not start with '__' — reserved)
scopeYesScope of the note. 'workspace' = shared across all agents; 'agent' = private to this agent (was 'global' pre-PR1); 'thread' = per-conversation; 'person' = per-contact. 'global' is accepted as a deprecation alias for 'agent'.
valueYesThe note content
pinnedNoPin this note so it's always loaded first. Default false.
memory_typeNoWhat kind of note: 'feedback' = a decision or correction by the owner or client (how to act), 'fact' = a durable fact about the client, their people or the business, 'context' (default) = anything else worth keeping. 'summary' and 'digest' are written by the system, 'procedural' is reserved.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
scope_ref_idNoReference ID — thread_id (for scope=thread) or person_id (for scope=person). Required for thread/person scope. In MCP mode (no thread context), must be passed explicitly.
target_agent_idNoTarget notebook. In agent mode optional (defaults to your own); required from MCP. Agents cannot target other agents' notebooks. Ignored when scope='workspace' (workspace memory is shared).
expires_in_hoursNoAuto-delete after N hours. Omit for permanent notes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / memory_type
      Added value: +{
      +  "description": "What kind of note: 'feedback' = a decision or correction by the owner or client (how to act), 'fact' = a durable fact about the client, their people or the business, 'context' (default) = anything else worth keeping. 'summary' and 'digest' are written by the system, 'procedural' is reserved.",
      +  "enum": [
      +    "context",
      +    "fact",
      +    "feedback"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  3. Added
  4. Removed
  5. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (which only declare non-read-only and non-destructive), the description discloses the upsert semantics ('If a note with the same key+scope exists it will be updated'), which is the single most important behavioral fact for a write tool. It doesn't say what the call returns or whether a version history is retained, and there is mild tension with idempotentHint=false given the described key+scope update-in-place, but nothing rises to a real contradiction.

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?

The core purpose is front-loaded in sentence one, the scope taxonomy in sentence two, and the collision and exclusion rules at the end. Every sentence carries distinct information, though the four-clause scope enumeration makes the block denser than strictly necessary.

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?

For a 9-parameter mutation tool with no output schema, the description covers the risky dimensions (visibility scope, upsert-on-collision, tool routing) while the remaining parameters are fully documented in the schema. The one real gap is return behavior — an agent is not told what it gets back or how to reference the saved note later.

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 decision-level meaning the schema lacks: the schema defines what each scope *is*, while the description says which scope to *pick* for which kind of content. The remaining seven parameters are left entirely to the schema, which is acceptable at full coverage.

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 opens with a specific verb and resource ('Save a fact or note into the agent's memory') and immediately differentiates itself from the sibling feedback_save, which handles behavioral rules. An agent can tell from this text alone which of notes_save / feedback_save / notes_search it wants.

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?

It gives an explicit when-to-use mapping for every scope value (shared facts and project conventions -> workspace, personal working notes -> agent, thread reminders -> thread, per-contact context -> person), plus a clear prohibition with the named alternative: 'Do NOT use this tool for behavioral rules or corrections — use feedback.save for those.' Both the positive and negative routing are stated, not inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.