XMemo

Dream Action

dream_action

Idempotent

Apply one Dream Workspace action the user explicitly asked for; never act on your own initiative.

accept_idea turns an idea into a todo; confirm_principle adopts a principle candidate; mute / unmute hides or restores one idea, principle or goal item; save_feed_card / save_feed_document saves a feed card or a feed edition; exclude_scope / include_scope stops or resumes Dream reading a scope in the owner's personal Dream settings. item_id is a card id from dream_view (for exclude_scope / include_scope, the scope label). Repeating an applied action returns status already_applied without a second write. Every result carries a receipt with a SHA-256 digest. Gates and protected-item checks apply; a run digest card cannot be changed.

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": {
      "action": "<action>",
      "item_id": "<item_id>"
    },
    "name": "dream_action"
  }
}

Input Schema

Name	Required	Description	Default
`scope`	No	personal (default) or project; project_key also selects the project space.	personal
`action`	Yes	One of accept_idea, confirm_principle, mute, unmute, save_feed_card, save_feed_document, exclude_scope, include_scope.
`item_id`	Yes	Card id from dream_view; for exclude_scope and include_scope, the scope label.
`payload`	No	Optional action data. save_feed_card: {card: {...}}; save_feed_document: {document: {items: [...]}}; both accept run_id and supersedes_id. accept_idea: optional project_key. Other actions ignore it.
`project_key`	No	Optional project key for project-space items.
`client_mutation_id`	No	Optional id recorded as the receipt's action_id; a new UUID when omitted.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedNov 8, 2026

changedInput schema / properties / action / description

Previous value: -"Usage action or audit-event action filter, depending on the tool."New value: +"One of accept_idea, confirm_principle, mute, unmute, save_feed_card, save_feed_document, exclude_scope, include_scope."

removedInput schema / properties / action / title
```
Removed value: -"Action"
```

changedInput schema / properties / client_mutation_id / description

Previous value: -"Client-supplied idempotency key (1-128 chars); replaying the same request with it returns the recorded result without a second write."New value: +"Optional id recorded as the receipt's action_id; a new UUID when omitted."

removedInput schema / properties / client_mutation_id / title
```
Removed value: -"Client Mutation Id"
```

changedInput schema / properties / item_id / description

Previous value: -"Input value for the Dream Action tool."New value: +"Card id from dream_view; for exclude_scope and include_scope, the scope label."

removedInput schema / properties / item_id / title
```
Removed value: -"Item Id"
```

changedInput schema / properties / payload / description

Previous value: -"Input value for the Dream Action tool."New value: +"Optional action data. save_feed_card: {card: {...}}; save_feed_document: {document: {items: [...]}}; both accept run_id and supersedes_id. accept_idea: optional project_key. Other actions ignore it."

removedInput schema / properties / payload / title
```
Removed value: -"Payload"
```

changedInput schema / properties / project_key / description

Previous value: -"Input value for the Dream Action tool."New value: +"Optional project key for project-space items."

removedInput schema / properties / project_key / title
```
Removed value: -"Project Key"
```

changedInput schema / properties / scope / description

Previous value: -"Optional scope that narrows memory access; leave blank for the token default."New value: +"personal (default) or project; project_key also selects the project space."

removedInput schema / properties / scope / title
```
Removed value: -"Scope"
```
removedInput schema / title
```
Removed value: -"dream_actionArguments"
```
removedOutput schema / properties / result / title
```
Removed value: -"Result"
```
removedOutput schema / title
```
Removed value: -"dream_actionOutput"
```

AddedOct 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations: idempotency is made concrete ("Repeating an applied action returns status already_applied without a second write"), and it discloses gates, protected-item checks, a SHA-256 receipt on every result, and the immutability of a run digest card. The immutability note is especially useful next to destructiveHint=false, since it tells the agent which target genuinely cannot be undone.

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 hard constraint in the first sentence, then the action glossary, then identifier and behavior notes — every line carries weight and there is no filler. The action glossary is a single long run-on sentence, which is dense but still scannable.

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 six-parameter multi-action mutation tool, the description covers when to act, what each action does, where item_id comes from, and what happens on repeat. An output schema already covers return shape, so the added note about receipts and digests is bonus rather than a gap-filler.

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 real meaning to the action parameter by explaining the effect of each enumerated value (accept_idea turns an idea into a todo, mute hides one item, exclude_scope stops Dream reading a scope). The item_id explanation duplicates the schema field almost verbatim, which caps it below 5.

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 ("Apply one Dream Workspace action") and then enumerates all eight action values with a one-clause gloss of each, so the agent knows exactly what accept_idea, mute, exclude_scope and the rest do. It is clearly distinguished from the read-side sibling dream_view, which is named as the source of item_id.

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 precondition ("the user explicitly asked for; never act on your own initiative") and a clear provenance rule for item_id from dream_view. It stops short of naming when a different mutation path is preferable (e.g. propose_todo_mutation vs accept_idea), so routing against the wider sibling set is still partly inferred.

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

All XMemo 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.