Skip to main content
Glama

muninn_onboard

Read-onlyIdempotent

Set up Muninn with the user. Call this when the user asks to set up Muninn, says they have just signed up, says their memory is empty, when muninn_session_boot comes back with nothing in it, or when they want a project instruction for a Claude Project. Returns {memoryCount, verified, hasIdentity, starterInstruction, projectInstruction?}. memoryCount is what the user's Memory Map shows, so 0 means an empty map. verified:false means the account is read-only until the user clicks the link in their "Verify your Muninn account" email, so every save will be refused; say that plainly. hasIdentity:true means the user has already saved who they are. A guided first-run setup is the onboard prompt, which the user picks in their client; mention it if they want one. starterInstruction is an optional standing instruction, written for the assistant in use, that the user can paste into their own assistant settings if they want Muninn loaded at the start of every conversation. Offer it only after at least one memory is saved, or if they ask why their assistant does not use Muninn on its own, and tell them what it does before they paste it. PROJECT INSTRUCTION: pass project (and persona and purpose if the user gave them) to also get projectInstruction, a short text for the user to paste into a Claude Project's instructions. It names the project and persona, loads Muninn at the start of each conversation in that project, and keeps the user's voice and rules in Muninn rather than in the file. Show it to the user as text to copy; ask for the project's purpose if they have not said it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "muninn_onboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
personaNoPersona name to load in that project, e.g. 'Ava'. Only one the user has (see muninn_persona_save).
projectNoProject slug for a Claude Project instruction, e.g. 'book-2026'. Omit unless the user wants a project instruction.
purposeNoTwo or three sentences, in the user's words, on what the project is for and what it is not for.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / persona
      Added value: +{
      +  "description": "Persona name to load in that project, e.g. 'Ava'. Only one the user has (see muninn_persona_save).",
      +  "type": "string"
      +}
    • addedInput schema / properties / project
      Added value: +{
      +  "description": "Project slug for a Claude Project instruction, e.g. 'book-2026'. Omit unless the user wants a project instruction.",
      +  "pattern": "^[a-z0-9][a-z0-9-]{0,63}$",
      +  "type": "string"
      +}
    • addedInput schema / properties / purpose
      Added value: +{
      +  "description": "Two or three sentences, in the user's words, on what the project is for and what it is not for.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it decodes return fields (memoryCount = what the Memory Map shows, verified:false = account read-only and every save will be refused, hasIdentity = identity already saved) and prescribes how to communicate the unverified state. That is exactly the operational context an agent cannot get from annotations.

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 trigger list, then return semantics, then the two optional add-ons, which is a sensible order. It is long and contains some redundancy (the starter instruction is explained twice over several sentences, and the PROJECT INSTRUCTION heading repeats the project parameter's own wording), keeping it out of the top band.

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?

For a zero-required-parameter onboarding tool with no output schema, the description covers return shape, the meaning of each flag, the read-only failure mode, and how to route to each optional follow-up. Nothing an agent needs in order to call it or narrate the result is missing.

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 coverage is 100%, so the baseline is 3. The description does add selection logic beyond the schema - pass project, persona and purpose only when the user wants a project instruction - but it does not add format constraints or clarify how persona interacts with projects beyond what the field descriptions already say.

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 ("Set up Muninn with the user") and immediately bounds its scope with concrete triggers, including the sibling condition "when muninn_session_boot comes back with nothing in it." It also disambiguates the secondary capability (generating a Claude Project instruction) so an agent can tell it apart from the boot/session tool.

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 an explicit trigger list (user asks to set up, just signed up, empty memory, empty boot response, wants a project instruction) plus a when-not/sequencing rule: only offer starterInstruction after at least one memory is saved, or if the user asks why the assistant doesn't use Muninn. It also names the prerequisite for the project branch (ask for purpose if not given).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources