Skip to main content
Glama
Sign In
Commonly

Commonly

Official
by Team-Commonly
OverviewSchemaRelated ServersDiscussionsAdmin
JavaScript

commonly_save_my_memory

Save a durable decision, project fact, or stated preference to this agent's persistent memory so it carries across sessions and runtimes. Record proactively instead of re-asking.

Instructions

Save a durable takeaway to this agent's memory — the things a teammate would remember next week (decisions, project facts, a preference the human stated), not chit-chat. Your memory persists across every session and every runtime you connect from, so record proactively and read it back (commonly_read_agent_memory) instead of re-asking. ADR-003 Phase 2: write ONE section of this agent's memory envelope via patch-mode sync. Sections: soul | long_term | daily | dedup_state | relationships | shared | runtime_meta. For daily/relationships pass entries (array). For single-object sections pass content (and optional visibility). Do not pass both entries and content. Sibling sections are preserved.

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": {
      "section": "<section>"
    },
    "name": "commonly_save_my_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentNo
entriesNo
sectionYes
visibilityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.16

TDQS

A4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does meaningful work: it discloses persistence scope ('across every session and every runtime you connect from'), the underlying write semantics ('patch-mode sync'), and the crucial non-destructive guarantee that 'Sibling sections are preserved.' It also warns against an invalid call combination ('Do not pass both `entries` and `content`'). It does not cover failure modes, size limits, or what a successful save returns.

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 purpose and the include/exclude criterion are front-loaded, and the section-to-parameter rules follow in a scannable order. The 'ADR-003 Phase 2' reference is internal jargon that adds no decision-relevant information for an agent and could be dropped without loss.

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 annotations, no output schema, and four undocumented parameters, the description is the only source of behavioral and structural information, and it covers persistence, patch semantics, preservation of sibling sections, and per-section parameter routing. The remaining holes are the `visibility` value set and the `entries` element structure, which are needed for a fully correct invocation.

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 description coverage is 0%, so the description must compensate, and it largely does: it enumerates the seven valid `section` values in prose, explains the `entries` vs `content` split by section, and flags `visibility` as optional. Two gaps remain that affect call correctness: the accepted values for `visibility` are never stated, and the element shape of the `entries` array is left undefined.

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 description states a specific verb and resource ('Save a durable takeaway to this agent's memory') and sharpens it with a concrete inclusion criterion ('decisions, project facts, a preference the human stated'), plus an exclusion ('not chit-chat'). It also names the read counterpart, commonly_read_agent_memory. It stops short of distinguishing itself from the sibling commonly_write_agent_memory, which an agent could plausibly confuse it with.

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?

It gives clear when-to-use guidance ('record proactively and read it back ... instead of re-asking') and a concrete rule for which parameter to use per section ('For `daily`/`relationships` pass `entries` ... For single-object sections pass `content`'). What is missing is any guidance on when to prefer this over commonly_write_agent_memory or commonly_checkpoint_event, so the routing decision among write-side siblings remains ambiguous.

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