Skip to main content
Glama

dream_tidy_up

Read-only

The Dream: in notes changed in the last N days (or one folder) finds broken [[links]], empty or still-template notes, long decision logs, with a script to follow (duplicates you look for yourself, reading); ask once before anything that loses content. Use on 'dream', 'sogna', 'tidy up', 'riordina' or the Dream email's sentence (a dated «Dream of …» — or the older «pre-dream of …» — means saved=true).

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": "dream_tidy_up"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo1-15, default 7
pathNoFolder: all its notes (max 300)
savedNoUse the saved Dream report. Set it when the user's sentence names a dated Dream: «the Dream of 26 September», «il Sogno del 26 settembre», or the older wording «the pre-dream of …» / «il pre-sogno del …» (same thing).
workspaceNoUsually omit; else brain id (as in search hits), 'mine', or owner name/email.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / saved / description
      Previous value: -"Use the saved pre-dream (when the user mentions one)"New value: +"Use the saved Dream report. Set it when the user's sentence names a dated Dream: «the Dream of 26 September», «il Sogno del 26 settembre», or the older wording «the pre-dream of …» / «il pre-sogno del …» (same thing)."
  2. Changed4 schema fields changed
    • changedInput schema / properties / days / description
      Previous value: -"How many days back to look (1-15): only the notes changed in that period are checked, plus the older notes they are close to. «yesterday» = 1, «this week» = 7. Default 7. Ignored when path is given."New value: +"1-15, default 7"
    • changedInput schema / properties / path / description
      Previous value: -"A folder: dream on every note inside it, whatever its age (up to 300 notes)."New value: +"Folder: all its notes (max 300)"
    • changedInput schema / properties / saved / description
      Previous value: -"true = use the pre-dream Cobrain already saved (the list in the email and on the Dream page) instead of checking again. Pass it when the user's sentence mentions «the pre-dream of <date>» / «il pre-sogno del <date>»."New value: +"Use the saved pre-dream (when the user mentions one)"
    • changedInput schema / properties / workspace / description
      Previous value: -"Brain to act on: its id, «mio» (yours), or the owner's name/email as shown by search. Usually OMIT it: a path that already lives in one brain is found there, for reads and writes alike. Pass it only when the tool tells you to (a NEW branch, or one that exists in several brains) — with the brain the user named; when they were not explicit ASK THEM. A brain where the branch does not exist is refused even if you name it."New value: +"Usually omit; else brain id (as in search hits), 'mine', or owner name/email."
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description adds genuinely new behavioral context — that it emits a script to follow, that the agent must 'ask once before anything that loses content,' and that duplicate detection is out of scope. The confirmation requirement is the kind of workflow detail annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense run-on sentence with heavy parentheticals and em-dashes; the invocation triggers sit at the end rather than being front-loaded. Little is redundant, but the packaging makes it slow to parse under time pressure.

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

Completeness3/5

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

There is no output schema, and the description never clarifies what actually comes back — a report, a proposed action list, or the 'script' — nor its approximate size or how the confirm step is performed. For a multi-mode analysis tool (days vs path vs saved), that leaves a meaningful gap.

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 baseline is 3, but the description adds real meaning: it frames days and path as alternative scopes ('or one folder') and binds saved=true to the dated «Dream of …» phrasing. That mutual-exclusivity nuance is not in the schema.

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?

The description names a specific resource (notes changed in the last N days or one folder) and enumerates exactly what it hunts for: broken [[links]], empty/template notes, long decision logs. It is clearly distinguishable from siblings like recent_changes or find_notes, though the opening framing ('The Dream:') is idiosyncratic and delays the verb.

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 lists concrete invocation triggers ('dream', 'sogna', 'tidy up', 'riordina', the Dream email sentence) and explicitly scopes out one job: 'duplicates you look for yourself, reading', routing the agent elsewhere. No explicit when-not conditions beyond that, but the context is unambiguous.

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