Skip to main content
Glama
CROW: LLM Wiki

CROW: LLM Wiki

Official

remember

Stores durable facts, decisions, and preferences in long-term memory, auto-filing each note into the correct Markdown wiki folder and merging related entries.

Instructions

Save a fact, decision or text in the long-term memory, in the folder and note where it belongs.

Call it when the user asks you to remember or note something, and on your own when something durable is settled (a decision and why, a preference, a fact about a project or a person): one topic per call, self-contained. For a document on disk, use remember_file. A classifier picks the folder and whether to merge into the note on the same subject; a model writes the note and links related ones. Returns {action: created | merged | unchanged, note, folder, related}. Adds or merges, never deletes. Never store secrets. With your models, it returns a job with requests instead: answer them with reply.

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": {
      "text": "<text>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesWhat to keep, self-contained; Markdown is fine
titleNoA short title; empty: the memory names it

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.4

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only give the safety triad (writable, closed-world, non-destructive); the description goes well past that by disclosing that a classifier picks the folder and merge target, a model writes and links the note, and the result is created/merged/unchanged. It also flags the secrets prohibition and the surprising conditional path where some models get back a `job` of requests to answer via `reply`. The only softness is that the `job` path is compressed into one clause with no indication of how often it occurs.

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?

Front-loaded with purpose, then trigger conditions, then the alternative, then mechanics — a sensible information order with no filler sentences. It is dense with semicolon-chained clauses, though, and the trailing `job`/`reply` note reads as an afterthought rather than a structured conditional.

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?

An output schema exists, yet the description still names the return shape briefly, and it covers the non-obvious operational cases (merge vs create, no deletes, classifier-assigned folder, async job variant). For a two-parameter tool with full schema coverage, nothing an agent needs in order to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds a real constraint not present in the schema: one topic per call and self-contained text. That meaningfully shapes how `text` should be composed beyond the schema's 'What to keep, self-contained; Markdown is fine'.

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?

Opens with a concrete verb and resource: save a fact, decision or text into long-term memory, placed in the folder and note where it belongs. It also carves out the boundary against `remember_file` for on-disk documents, so the agent can separate the two tools without inspecting either schema.

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?

Gives both trigger modes explicitly — when the user asks, and autonomously when something durable is settled — with concrete examples (decision and rationale, preference, project or person fact). It also states a counter-case with a named alternative: use `remember_file` for documents on disk.

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