Skip to main content
Glama

Restore Restart Snapshot

restore_restart_snapshot
Destructive

Resume previous work from a saved snapshot. Relevant when the user asks to resume/restart or after context loss. By default it overwrites the current working state with the snapshot's state and writes a restore event to the timeline. To only inspect a snapshot, pass restore_state=false and record_restore_event=false with its snapshot_id; without a snapshot_id, when no saved snapshot matches, a new snapshot of the current working state is saved first.

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": "restore_restart_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoOptional scope that narrows memory access; leave blank for the token default.
bucketNoMemory bucket or namespace to read from or write to; use % only for tools that support wildcard reads.work
state_keyNoWorking-state key to save, snapshot, or restore, such as active_task.
snapshot_idNoExact restart snapshot memory ID to restore.
ttl_secondsNoTime-to-live in seconds for working state or restart snapshot records.
restore_stateNoWhether restore_restart_snapshot should restore the saved working-state record.
source_session_idNoSession ID whose saved restart snapshot should be restored.
target_session_idNoSession ID to associate with restored state and restore events.
record_restore_eventNoWhether to write a timeline event after restoring a restart snapshot.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description goes beyond that by naming exactly what is destroyed — the current working state is overwritten — and disclosing the timeline event write. It also reveals the non-obvious fallback that a new snapshot of current state is saved when no snapshot matches, though the phrasing of that fallback is hard to parse and reversibility is never stated.

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?

Purpose is front-loaded, followed by the default behavior and then the escape hatch, which is the right ordering for an agent deciding whether to call it. The final sentence packs three conditional clauses into one convoluted statement that costs readability.

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

Completeness4/5

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

With nine fully documented parameters, an output schema, and complete annotations, the description carries the right residual burden: it explains the destructive default, the side-effect event, and the fallback snapshot. Remaining gaps are the session-id parameters and whether a restore can be undone, which matter for a destructive tool.

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; the description earns above that by explaining the interaction between restore_state, record_restore_event, and snapshot_id for the inspect-only pattern, which the per-field schema text does not convey. It leaves source_session_id versus target_session_id and the scope/bucket/ttl_seconds interaction undiscussed.

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?

"Resume previous work from a saved snapshot" is a specific verb+resource statement that an agent can act on. It does not, however, contrast itself with adjacent tools like restore_memory or update_state, so the agent must infer from the name alone which restore path applies.

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 gives concrete triggering conditions ("user asks to resume/restart or after context loss") and explicitly carves out an inspection-only mode with restore_state=false and record_restore_event=false. It stops short of naming a sibling tool to use instead when the agent wants a non-destructive read, which would have made it a 5.

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.