Skip to main content
Glama

memory_store

Persist a string value under a key to survive across sessions, with confirmation of new or overwritten writes. Use for preferences, agent memos, or named facts that need exact recall.

Instructions

Persist a string value under a key in ContextPulse's local memory database.

Returns confirmation with the stored key and an indication of whether the write was new or an overwrite.

USE WHEN: you need a value to survive across sessions and be recallable by exact key (preferences, agent memos, named facts). NOT FOR: fuzzy retrieval (use memory_search) or semantic similarity (use memory_semantic_search). For ephemeral session state, hold it in agent context — don't bloat persistent memory. ALTERNATIVES: route_to_journal (timestamped narrative log) is better for journaling.

BEHAVIOR: SIDE EFFECT — overwrites any existing value at the same key (last-write-wins). Persists to the local SQLite memory database; survives daemon restart. Idempotent for identical (key, value, tag) tuples. No auth or rate limits — local only.

PARAMETERS: key: stable identifier. ASCII recommended. Max 256 chars. Required. value: string to persist. Max ~1 MB. Required. tag: optional grouping label, queryable via memory_list(tag=...).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYes
valueYes
tagNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

No annotations provided, but description discloses side effect (overwrite), persistence (survives daemon restart), idempotency, and no auth/rate limits.

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?

Well-structured with sections (USE WHEN, NOT FOR, ALTERNATIVES, BEHAVIOR, PARAMETERS). Every sentence adds value; no fluff.

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

Completeness5/5

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

With output schema present, description appropriately notes return value (confirmation with key and new/overwrite indication). Covers all necessary aspects for a store operation.

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

Parameters5/5

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

Schema lacks descriptions (0% coverage), but description adds crucial details: key max 256 chars ASCII, value max ~1 MB, tag optional grouping label queryable via memory_list(tag=...).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Persist a string value under a key' and distinguishes from siblings like memory_search, memory_semantic_search, and route_to_journal.

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

Usage Guidelines5/5

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

Explicit 'USE WHEN' and 'NOT FOR' sections with named alternatives (memory_search, memory_semantic_search, route_to_journal) and guidance on ephemeral vs persistent storage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ContextPulse/contextpulse'

If you have feedback or need assistance with the MCP directory API, please join our Discord server