Skip to main content
Glama

memory_save

Save and update durable cross-session project memory for architecture, conventions, commands, constraints, pitfalls, context, and facts, so project chats retain decisions and knowledge.

Instructions

Save or idempotently update a durable cross-session project memory (architecture, convention, command, constraint, pitfall, context, or fact).

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": "memory_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoStable kebab-case slug key for idempotent updates.
tagsNo
titleYes
contentYes
categoryNo
memory_idNoExisting memory ID to update.
confidenceNo
file_pathsNo
project_idNoOptional project ID (auto-resolved when omitted).
inject_modeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does add genuine value by disclosing idempotent update behavior, but it says nothing about collision handling on 'key', permissions, what an update overwrites, or how memory_id and key interact.

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?

A single well-formed sentence with the action front-loaded and no filler. It is efficient, but the brevity is achieved by omitting information the agent needs rather than by tight phrasing.

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?

For a 10-parameter mutation tool with no annotations, no output schema, and sparse schema descriptions, the description is far too thin. It leaves the agent guessing about the two update paths (key-based upsert vs memory_id) and the effect of inject_mode and confidence.

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

Parameters2/5

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

Only 30% of the 10 parameters carry schema descriptions, so the description needs to compensate and does not. The category list it cites merely restates the enum values, and nothing explains key vs memory_id, project_id auto-resolution, confidence, or inject_mode.

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 specific verbs (save / idempotently update) and a specific resource (durable cross-session project memory), and even enumerates the record categories. An agent can tell this apart from memory_list or memory_delete by verb alone, though the distinction from the near-identical ui_save_memory and note_save is not drawn.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The phrase 'durable cross-session project memory' implies persistence semantics versus a note, but the agent must infer when to reach for this over note_save or ui_save_memory.

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