Skip to main content
Glama
Kaede Recall MCP

Kaede Recall MCP

memory-write

Store one durable memory with automatic deduplication, linking and superseding in a single call. Use it to persist facts, preferences, decisions or procedures for later recall.

Instructions

Store one durable memory. Dedupes, links and supersedes in one call.

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": {
      "kind": "<kind>",
      "text": "<text>"
    },
    "name": "memory-write"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesfact, preference, profile, decision, problem, procedure, trace or doc
tagsNoComma separated tags
textYesThe memory itself, self contained
linksNoComma separated relations, e.g. fixed_by:<id>,depends_on:<id>
scopeNoglobal or project:<id>global
sourceNoWhere it came from
projectNoProject id, optional
summaryNoOne line trigger, optional
entitiesNoComma separated aliases, e.g. rpi,raspberry-pi,systemd
supersedes_idNoId of the memory this replaces

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.10.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden of behavioral disclosure. "Dedupes, links and supersedes in one call" usefully reveals implicit automatic behavior, but it never says what dedupe does (merge? reject? return existing id?), what happens to a superseded memory, or whether the call is idempotent.

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, front-loaded with the core action and zero filler. Every clause adds signal.

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?

For a 10-parameter mutation tool with no annotations and no output schema, the description should at least state what the call returns (presumably a memory id) and what dedupe and supersede do to existing data. It covers the headline behavior but leaves an agent unable to predict side effects or results.

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 100% across all 10 parameters, so the schema already explains kind, tags, links, scope, entities and supersedes_id. The description adds no parameter-level meaning beyond the hint that dedupe and linking happen automatically; the baseline of 3 is appropriate.

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 a specific verb and resource ("Store one durable memory"), so an agent can distinguish it from memory-recall and memory-delete without opening the schema. The word "supersedes" blurs the line with memory-update, but the verb-plus-resource phrasing remains clear.

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?

The definition implicitly signals use for creating a new durable memory: "Store one durable memory" and "Dedupes... in one call." It names no alternative and gives no exclusion such as when to use memory-update instead of superseding through this tool; that overlap with memory-update is never addressed.

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