Skip to main content
Glama

Revert a Playground agent run’s canvas changes

playground_run_revert
DestructiveIdempotent

Undo every canvas change one agent run made, newest first, as one new revision. If someone has edited those nodes since, nothing changes and the conflicting node/edge IDs are returned; pass force=true only after confirming the later edits may be discarded. Generated media and credits are not refunded by a revert. Returns revert status, revision and any conflicting or overridden changes.

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": {
      "projectId": "<projectId>",
      "runId": "<runId>",
      "expectedRevision": "<expectedRevision>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "playground_run_revert"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoWhether to override detected conflicts while reverting; use only when the user intends to overwrite those later changes.
runIdYesRun ID returned by preparation or execution for this project.
projectIdYesID of the Playground project chosen for this task; obtain it from project creation, an explicit project link or current context.
idempotencyKeyYesUnique key for this request; reuse only when retrying the identical request after a lost response. Use a new key after quoting or changing inputs.
expectedRevisionYesCurrent canvas revision from canvas_read; on revision_conflict, read again and rebuild the change.

Output Schema

NameRequiredDescriptionDefault
runIdNo
statusYes
replayedYes
revisionYes
conflictsNo
overrodeConflictsNo
revertedRevisionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses conflict detection semantics (if nodes were edited since, nothing changes), what is returned on conflict (conflicting node/edge IDs), the override path, and a non-obvious side effect — generated media and credits are not refunded. Annotations already flag destructive/idempotent, and the description adds the operational detail that matters for a destructive write.

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

Conciseness5/5

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

Three dense sentences, front-loaded with the action, then the conflict/force rule, then the non-refund caveat and return shape. No filler or repetition.

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 destructive, conflict-prone mutation with five parameters, the description covers the failure mode, the override, the cost caveat, and the response shape; an output schema exists so return details need not be exhaustive.

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

Parameters3/5

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

Schema coverage is 100% and the schema already documents force ('use only when the user intends to overwrite those later changes') and expectedRevision (rebuild on revision_conflict). The description's force guidance largely restates that, adding only the conflict framing; baseline 3 is appropriate.

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 (undo every canvas change one agent run made) plus the mechanism (as one new revision, newest first). The 'one agent run' scope distinguishes it from canvas-level operations such as playground_canvas_snapshot_restore without needing to name them.

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 a clear conditional rule for the risky path: pass force=true only after confirming the later edits may be discarded, and implies the default no-force path is the safe one. It does not name a sibling alternative (e.g. snapshot restore) for undoing changes not tied to a run, so it stops short of explicit when-not guidance.

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.