Skip to main content
Glama
sleepunit-agents

loom

by sleepunit-agents
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

bootstrap

Destructive

Initialize a new loom identity by generating identity, preference, and self-model files from a short onboarding interview, then return runtime setup instructions.

Instructions

Initialize a new loom identity from scratch. Generates IDENTITY.md, preferences.md, and self-model.md from an onboarding interview, then returns setup instructions for the requested runtimes. The interview is four questions — the user's name, the agent's name, a one-line purpose, a one-line voice; everything structural (continuity model, memory tiers, reflection, honesty) is written by the scaffold, so do not ask for it. Will not overwrite existing files unless force is true.

Input Schema

NameRequiredDescriptionDefault
nameYesName for the agent identity (e.g. "Aria")
userNoThe human this agent works with — their name, not the agent's
forceNoOverwrite existing identity files (default: false)
voiceYesCommunication style and personality, one line
clientsNoRuntimes to generate setup instructions for: "claude-code", "gemini-cli", or any custom runtime name (uses a generic template)
purposeYesWhat this agent exists to do — its reason for being, one line
preferencesNoSeed preferences about the user or working style

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changedv0.5.0
    • changedInput schema / properties / purpose / description
      Previous value: -"What this agent exists to do — its reason for being"New value: +"What this agent exists to do — its reason for being, one line"
    • addedInput schema / properties / user
      Added value: +{
+  "description": "The human this agent works with — their name, not the agent's",
+  "type": "string"
+}
    • changedInput schema / properties / voice / description
      Previous value: -"Communication style and personality"New value: +"Communication style and personality, one line"
  3. First observedv0.4.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description usefully narrows that by stating files are not overwritten unless force is true, plus enumerating exactly what gets generated. It adds real context beyond the safety flags, but omits any auth/permission requirements or what a partial failure leaves behind.

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?

Four sentences, front-loaded with what it does and what it produces before the interview and guardrail details. Slightly dense but each clause adds information an agent needs to run the interview correctly.

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?

For a 7-param mutation tool with no output schema, it covers generation targets, the guarded overwrite, the interview scope, and what the return contains (setup instructions). Only minor gaps remain, e.g. behavior when clients is omitted.

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 already 100%, so the baseline is 3, and the description goes further by mapping the required params to interview questions (name, user, purpose, voice) and clarifying the clients runtimes ('claude-code', 'gemini-cli', or generic template). The force guard is restated for emphasis.

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?

States a specific verb and resource — "Initialize a new loom identity from scratch" — and names the concrete artifacts produced (IDENTITY.md, preferences.md, self-model.md), which cleanly separates it from siblings like update_identity, identity, and harness_init.

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?

"From scratch" plus the four-question interview framing makes the use case clear: greenfield identity creation, not editing. It also gives a concrete when-NOT to ask instruction ("do not ask for it") for structural fields, though it never names update_identity as the alternative for existing identities.

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