Skip to main content
Glama
Sign In
Geniuz

Geniuz

by jackccrawford
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

keep

Store important user preferences, decisions, and project context so future sessions can find them by meaning rather than keywords.

Instructions

Keep something worth remembering for future sessions. Use this when you learn something important about the user — their preferences, decisions, client details, project context, or anything they would not want to repeat. Your future self will find it by meaning, not keywords. Keep more than you think you should — storage is free, forgetting is expensive.

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>",
      "gist": "<gist>"
    },
    "name": "keep"
  }
}

Input Schema

NameRequiredDescriptionDefault
gistYesA one-line summary for finding this later. Format: 'category: key insight'. Example: 'client: Maria — Q2 retention focus, $40K budget'
folderNoWhich folder to use, by name or 8-character ID. Choose one with the folders tool. Left out, this uses the current folder. An unknown name is an error, never a different folder.
threadNoOptional. Short UUID or address of a memory in the same folder to thread this to. Builds chains — prospect to client, draft to final, problem to solution. A memory in another folder can't be threaded to: keep this in that folder, or put its address in the content instead.
contentYesThe full detail. Write for a future you that knows nothing about this session. Include names, numbers, decisions, reasoning, context.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv5.0.2
    • changedInput schema / properties / thread / description
      Previous value: -"Optional. Short UUID of a previous memory to thread this to. Builds chains — prospect to client, draft to final, problem to solution."New value: +"Optional. Short UUID or address of a memory in the same folder to thread this to. Builds chains — prospect to client, draft to final, problem to solution. A memory in another folder can't be threaded to: keep this in that folder, or put its address in the content instead."
  2. Addedv5.0.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavioral traits: persistence across sessions, semantic (not keyword) retrieval, and that storage cost is effectively zero. It does not address duplicate handling, mutability of an existing memory, or what is returned on success — relevant since the thread parameter depends on a memory address.

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 the action, then the trigger, then the retrieval rationale. The closing "storage is free, forgetting is expensive" is persuasive framing rather than specification, but it does encode a real usage policy, so it mostly earns its place.

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

Completeness4/5

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

Four parameters with full schema coverage and no output schema means the description needn't explain return values, and it covers purpose, trigger, and persistence well. The one gap is that nothing tells an agent where the address for threading comes from, which the thread parameter assumes it already has.

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%, so the schema already explains content, gist, folder, and thread in detail, including error behavior for unknown folder names. The description only adds the retrieval-by-meaning rationale that motivates the gist field. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

"Keep something worth remembering for future sessions" states a specific verb (persist) and resource (a memory), and the line about future retrieval by meaning implicitly separates it from the read-only sibling recall. It stops short of naming recall or folders explicitly, so the sibling boundary is inferred rather than stated.

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

Usage Guidelines4/5

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

It gives a concrete trigger ("when you learn something important about the user") and enumerates what qualifies: preferences, decisions, client details, project context. It also nudges toward over-use rather than under-use. What's missing is an explicit when-not or a named alternative such as recall or folders for lookup tasks.

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

Deploy Server

Other Tools