Skip to main content
Glama

hjarni

by com.hjarni
OverviewDiscussionsAdmin

containers-update

DestructiveIdempotent

Update a folder within the connected user's personal Hjarni account or an authorized team workspace — rename, set its icon (emoji), change description or negative_space (what does NOT belong here), move to a different parent, set display position, or archive/unarchive it. Works for both personal and team containers the current user can edit (team containers require the editor role). Refuses the space's root (root: true in containers-get); set that space's instructions with instructions-update instead, and pass parent_id null, not the root's id, for a top-level folder. Required: id (integer). Optional: name, emoji (pass null to clear it), description, negative_space (pass null to clear it), parent_id (null for root, must be in the same scope), position (integer, lower = first). Archiving: archived (boolean) archives or unarchives the folder itself; add include_notes: true to also retire/reactivate every note filed in it IN BULK, and include_nested: true to sweep nested sub-folders (and, with include_notes, their notes) too. This is THE way to retire a whole folder — e.g. a finished project or a large import whose notes keep surfacing in dashboards — in one call; never loop notes-update over each note for that. The response then includes containers_changed and notes_changed counts (rows actually flipped; note bodies are not returned). On team containers an include_nested sweep requires the editor role on every affected sub-folder. Caveat on reversing: an unarchive sweep reactivates EVERYTHING it touches — include_nested resurrects sub-folders, and include_notes resurrects notes, that the user had archived individually before the sweep. When that matters, unarchive selectively: archived: false on specific folders, and individual notes via notes-update. Unarchiving a nested folder also reactivates its archived ancestor folders, so the restored folder stays reachable. Find archived folders again later with containers-list scope 'archived'.

Input Schema

NameRequiredDescriptionDefault
idYesContainer ID (required)
nameNoNew name
emojiNoOne emoji shown as the folder's icon, e.g. "📦", or null to clear it back to the plain folder icon.
archivedNoArchive (true) or unarchive (false) the folder. On its own this only flags the folder; combine with include_notes/include_nested to retire its contents too.
positionNoDisplay order position (lower numbers appear first)
parent_idNoNew parent container ID, or null to move the container to root level. Must belong to the same scope as the container.
descriptionNoNew description
include_notesNoWith archived: also set the same archived state on every kept note filed in the folder (and in its sub-folders when include_nested is true), in one bulk update. Default: false.
include_nestedNoWith archived: apply the same archived state to all nested sub-folders as well. Default: false.
negative_spaceNoWhat does NOT belong in this folder, or null to clear it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / emoji
      Added value: +{
+  "description": "One emoji shown as the folder's icon, e.g. \"📦\", or null to clear it back to the plain folder icon.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. Changed3 schema fields changed
    • addedInput schema / properties / archived
      Added value: +{
+  "description": "Archive (true) or unarchive (false) the folder. On its own this only flags the folder; combine with include_notes/include_nested to retire its contents too.",
+  "type": "boolean"
+}
    • addedInput schema / properties / include_nested
      Added value: +{
+  "description": "With archived: apply the same archived state to all nested sub-folders as well. Default: false.",
+  "type": "boolean"
+}
    • addedInput schema / properties / include_notes
      Added value: +{
+  "description": "With archived: also set the same archived state on every kept note filed in the folder (and in its sub-folders when include_nested is true), in one bulk update. Default: false.",
+  "type": "boolean"
+}
  3. Changed2 schema fields changed
    • changedInput schema / properties / parent_id / description
      Previous value: -"New parent container ID (null for root). Must belong to the same scope as the container."New value: +"New parent container ID, or null to move the container to root level. Must belong to the same scope as the container."
    • changedInput schema / properties / parent_id / type
      Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]
  4. Changed1 schema field changed
    • addedInput schema / properties / negative_space
      Added value: +{
+  "description": "What does NOT belong in this folder, or null to clear it.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / parent_id / description
      Previous value: -"New parent container ID (null for root)"New value: +"New parent container ID (null for root). Must belong to the same scope as the container."
  6. Changed2 schema fields changed
    • changedInput schema / description
      Previous value: -"Update an existing container (rename, change description, move to a different parent, or set display position)."New value: +"Update an existing container."
    • changedInput schema / properties / id / description
      Previous value: -"Container ID"New value: +"Container ID (required)"
  7. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond annotations: discloses the response fields (containers_changed, notes_changed, no note bodies), the editor-role requirement for team sweeps and nested operations, and a detailed caveat that unarchive sweeps resurrect individually archived items and ancestor folders. The one gap is that the destructiveHint is only implicitly conveyed via the archive-sweep caveat rather than stated outright.

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?

Long but front-loaded: core capabilities first, then constraints, then archive mechanics, then reversal caveat. Nearly every sentence carries load, though the archive/unarchive paragraph is dense enough that some sentences could be tightened without loss.

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 10-parameter destructive update tool with no output schema, the description covers mutation semantics, permission requirements, bulk-sweep side effects, return counts, and reversal hazards — everything an agent needs to call it safely and correctly.

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 operational semantics not obvious from the schema: 'parent_id null, not the root's id' for top-level, parent must be in the same scope, and null-to-clear behavior for emoji/negative_space. It reinforces rather than fully duplicates the schema.

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 (update) and resource (folder/container) and enumerates the exact mutations available (rename, icon, description, negative_space, reparent, position, archive). It distinguishes itself from siblings by explicitly deferring space-level instructions to instructions-update and bulk note edits to notes-update.

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?

Explicitly declares when to use this tool (bulk folder retirement 'never loop notes-update'), when not to (root containers, use instructions-update), and offers the selective-unarchive alternative when reversal precision matters. Nothing is left to inference.

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

All hjarni toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources