Skip to main content
Glama

remember_decision

Save architectural decisions, coding conventions, bug root causes, or important context to MindGate's persistent memory so AI tools retain shared project knowledge across sessions and tools.

Instructions

Save an architectural decision, coding convention, bug root-cause, or important context into MindGate (بوابة العقل) so all AI tools remember it.

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": {
      "title": "<title>",
      "content": "<content>"
    },
    "name": "remember_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoOptional searchable keywords/tags.
titleYesConcise title summarizing the decision or context.
contentYesDetailed explanation, rationale, code patterns, or constraints.
categoryNoCategory of the memory record.
workspaceNoProject workspace identifier (e.g. 'ecommerce-api' or 'global'). Defaults to MINDGATE_DEFAULT_WORKSPACE or 'global'.
supersedesNoOptional numeric ID(s) of older memory records superseded/deprecated by this new decision.
source_agentNoName of the AI tool recording this memory (e.g. 'antigravity', 'opencode', 'codex').

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations provided, the description carries the full disclosure burden. It does add one genuinely useful behavioral fact — the record is shared so 'all AI tools remember it', i.e. a cross-tool persisting write — but says nothing about mutability of saved records, permission requirements, duplicate/conflict handling, or what the call returns.

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

Conciseness5/5

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

A single well-formed sentence: verb first, resource types enumerated, destination and payoff last. Nothing is padded and the most important content leads.

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

Completeness2/5

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

This is a 7-parameter mutation tool with no annotations and no output schema, yet the description never mentions supersedes-based versioning, the workspace scoping model, or how records relate to later updates. The rich schema rescues the parameters, but the description leaves the agent without the write semantics it would need to use this well.

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 100%, so the schema already documents workspace defaults, supersedes IDs, source_agent, and tags, making the baseline 3. The description nudges slightly above baseline by mapping its enumerated record types onto the category enum ('architectural decision', 'convention', 'bug root-cause'), giving the agent a hint about which category value to pick.

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 gives a specific verb ('Save') plus an enumerated set of resource types — architectural decision, coding convention, bug root-cause, context — and names the destination (MindGate). That is enough to distinguish it from read-side siblings like recall_context or list-like tools. It stops short of explicitly contrasting with write siblings such as update_memory or log_session_summary, which keeps it off a 5.

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?

Usage is only implied: the agent infers it should call this when it has produced a durable decision worth persisting ('so all AI tools remember it'). There is no explicit when-not guidance and no named alternative for updating or deprecating an existing record, even though deprecate_memory, update_memory, and log_session_summary exist as siblings.

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