Skip to main content
Glama

Promote a fact to durable memory (writes + git-commit, gated)

memory_promote

Promote a durable fact into MEMORY.md with provenance tagging, source-class and pointer assignment, and a git commit, pausing for one-time user approval before writing.

Instructions

Curate a durable fact into MEMORY.md and git-commit it (provenance-tagged). This is a GATED action: it pauses and shows the fact to the user for a one-time approval before writing — you do NOT need to ask for confirmation separately first; just call it. Set sourceClass from where the fact came from — use 'untrusted-derived' for anything originating from invite/web/quarantined content (it requires confirmation). pointer is a reference back to the source (daily-log timestamp, message id, record id).

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": {
      "content": "<content>",
      "sourceClass": "<sourceClass>",
      "pointer": "<pointer>"
    },
    "name": "memory_promote"
  }
}

Input Schema

NameRequiredDescriptionDefault
contentYesThe durable fact text to promote (one fact).
pointerYesSource reference (daily-log timestamp / message id / record id).
sourceClassYesProvenance class of the fact.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses that this is a write plus git-commit, that execution pauses for a one-time approval, and that untrusted-derived provenance triggers an extra confirmation. It leaves out irreversibility, whether duplicate facts are deduplicated, and what a rejected approval 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?

Front-loads the action and the side effect, then the gating caveat, then parameter guidance. Sentences are dense but purposeful, with no filler. Minor redundancy in re-explaining pointer after the schema already covers it.

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 mutation tool with no annotations and no output schema, the description covers the essentials an agent needs before calling: what is written, that it commits, the approval gate, and how to classify provenance. The remaining gap is outcome reporting (what the agent sees after write or rejection).

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

Parameters3/5

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

Schema description coverage is 100%, so all three parameters are already documented, including the sourceClass enum and the pointer format. The description mostly restates these, though it adds the operational consequence that untrusted-derived sourceClass requires confirmation. That earns the baseline but not more.

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?

Opens with a specific verb and resource chain: curate a durable fact into MEMORY.md and git-commit it. That is far more concrete than the name alone. It stops short of 5 because it never names the sibling it is distinct from (commit_brain_edit, propose_brain_edit), leaving the agent to infer the boundary.

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?

Gives clear operational guidance for the gated flow: the tool pauses for a one-time user approval, so the agent should not ask for confirmation separately first. That removes a real decision point. It offers no when-not guidance, such as preferring propose_brain_edit for review-first flows or memory_forget for removal.

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