Muninn (munn.is)

muninn_picture_upload_finish

Write the picture memory after the user's photos arrived (check with muninn_picture_view first). The note is written in this session: what the photos show and what the moment was, in the user's words where you have them. Fill when, where and who only from what you actually know, and label each with its source: whenSource 'photo' (takenAt from muninn_picture_view), 'user' (they told you) or 'upload_time' (a photo just taken in the app, where upload time is capture time); whereSource 'user', 'device' (your device location tool, only when the user says the photo was taken here and now) or 'photo'. When the in-chat picker sent the fields, its labels map directly: 'When (from the photo's own metadata)' is whenSource 'photo', 'When (I said)' and 'Where (I said)' are 'user'. Never guess a place or a name from the pixels. The memory is tagged 'picture' plus your tags. Returns {success, memoryId, pictures}. Deleting this memory later deletes its photos.

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": {
      "memoryId": "<memoryId>",
      "note": "<note>"
    },
    "name": "muninn_picture_upload_finish"
  }
}

Input Schema

Name	Required	Description
`who`	No	People in or behind the photos, as the user named them.
`note`	Yes	The memory's text: what the photos are and what the moment meant.
`tags`	No	Tags, as for muninn_memory_add. 'picture' is added for you.
`when`	No	When the photos were taken: ISO date or date-time, e.g. 2026-09-29 or 2026-09-29T17:58:30+07:00.
`where`	No	Where the photos were taken, as a place name or address.
`project`	No	Project slug, as for muninn_memory_add.
`memoryId`	Yes	The memoryId from muninn_picture_upload_start or _direct.
`whenSource`	No	Where `when` came from. Required with `when`.
`whereSource`	No	Where `where` came from. Required with `where`.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 22, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only declare write/non-idempotent/non-destructive, so the description meaningfully adds: the note is session-scoped ('written in this session'), the return shape {success, memoryId, pictures}, and the cascade side effect ('Deleting this memory later deletes its photos'). It does not cover failure modes or what happens if photos have not actually arrived, despite the 'check with muninn_picture_view first' precondition.

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-loads the action and the precondition before the labeling rules, and most sentences carry distinct information. It is dense and slightly run-on in the source-label enumeration, but nothing is padding given 9 parameters.

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?

With no output schema, the description compensates by disclosing the return payload and the deletion cascade, and it ties the tool into the surrounding flow (view/start/direct, memoryId provenance, 'picture' auto-tag). An agent has everything it needs to finalize a picture memory correctly.

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

Parameters5/5

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

Well beyond the 100%-coverage schema: it defines the pragmatic meaning of each whenSource/whereSource enum value, gives the rule for 'upload_time' (capture time equals upload time in-app), and maps the in-chat picker labels directly onto source values. It also adds a constraint ('Never guess a place or a name from the pixels') that the schema cannot express.

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?

States a specific verb and resource ('Write the picture memory') and situates it in the upload flow ('after the user's photos arrived'). It distinguishes itself from the generic memory siblings via the 'picture' tag and the memoryId lineage from _upload_start/_direct, though it never explicitly contrasts with muninn_memory_add.

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?

Gives an explicit prerequisite ('check with muninn_picture_view first'), names the flow tools behind memoryId, and maps picker labels onto whenSource/whereSource values. It never states when NOT to use this tool or explicitly routes users to muninn_memory_add for non-picture memories.

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

All Muninn (munn.is) tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?