Skip to main content
Glama

memory_save

Idempotent

Save or update long-term memory for AI coding tools. Reuse a stable key or id to replace old values, skip duplicates, or batch short facts, environment details, and decisions.

Instructions

Save or update a memory. Same key or id updates; duplicates are skipped.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "memory_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoUpdate this memory; with no content, re-confirms it against current code
keyNoStable subject (os, db, test-cmd): same key replaces the old value
typeNo
filesNoProject files this depends on; flagged ?stale when they change
itemsNoBatch of memories instead of content
scopeNoglobal=about the user, project=this codebase; inferred if omitted
contentNoOne short fact, max 500 chars (omit when using items)
replaceNoUpdate a similar memory instead of adding

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully reinforces idempotency by explaining that same key or id updates and duplicates are skipped, but says nothing about scope inference consequences, how stale files are flagged, or what a batch 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.

Conciseness5/5

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

Two short sentences with zero waste; the primary action is front-loaded and the update rule follows immediately.

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 an 8-parameter tool with no required fields, batch `items` input, a `replace` toggle, and `files` dependency tracking — none of which the description mentions. With no output schema, the agent must open the schema anyway to learn about batching and staleness behavior, so the description is thin for the tool's complexity.

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 88%, so the baseline is 3. The description only restates the key/id update semantics that the schema already documents ("same key replaces the old value"), adding marginal value and leaving batch `items`, `files` staleness, and `replace` entirely to the schema.

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?

"Save or update a memory" states a specific verb and resource, and the second sentence clarifies the create-vs-update branch. It never names memory_search, memory_context, or memory_delete, so an agent gets no explicit differentiation from siblings.

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?

The description explains the update mechanism ("same key or id updates; duplicates are skipped") but gives no guidance on when to save versus when to search or read context with the sibling tools, and no prerequisites or exclusions.

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