recall-kit

memory_remember

Save a durable memory (fact, preference, decision, or project note) with its source and optional key so AI agents keep context across sessions, with new values for the same key replacing old ones.

Instructions

Save a durable memory. type: fact | preference | decision | project. source = where it came from (e.g. "user in Claude Code, 2026-11-10"). key = optional stable slot for single-valued facts; a new value for the same key supersedes the old one.

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>",
      "source": "<source>"
    },
    "name": "memory_remember"
  }
}

Input Schema

Name	Required	Default
`key`	No
`tags`	No
`type`	No	fact
`source`	Yes
`content`	Yes
`project`	No
`confidence`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

B3.4/5.0

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 burden. It usefully discloses the supersede/overwrite behavior for keyed memories, which is a real side effect an agent must know about, but it says nothing about deduplication, whether writes are idempotent, or how the default confidence of 0.9 affects storage.

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?

The core action is front-loaded in the first sentence and the parameter notes are terse and readable with no filler. The single dense paragraph of field notes is slightly harder to scan than a short list would be.

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

Completeness3/5

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

An output schema exists, so return values need not be described. However, for a 7-parameter write tool with zero annotation coverage, the definition leaves out the semantics of tags, project scope, and confidence, which an agent needs to call it well.

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 0% across 7 parameters, and the description explains only three of them: type (with the four allowed values, which the schema does not encode as an enum), source, and key. The tags, project, confidence, and content parameters receive no added meaning, leaving a substantial gap the schema does not fill.

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?

States a specific verb and resource ("Save a durable memory") and enumerates the allowed types, so the agent knows exactly what the call creates. It does not explicitly differentiate itself from close siblings such as memory_correct, which also produces stored memory state.

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 implied through the key semantics ("a new value for the same key supersedes the old one"), which hints at when to reuse a slot versus create a fresh memory. There is no explicit statement of when to prefer memory_correct or memory_forget over this tool, and no prerequisites are given.

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

Deploy Server