Branchwright MCP

restore_checkpoint

Idempotent

Restore a saved snapshot by appending a new revision that recovers prior knowledge and world clocks while preserving full history in Branchwright MCP.

Instructions

Only when the player explicitly requests it: append a revision restoring a saved snapshot, including knowledge and world clocks. Never erase history.

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": {
      "campaign_id": "<campaign_id>",
      "branch_id": "<branch_id>",
      "expected_revision": "<expected_revision>",
      "target_revision": "<target_revision>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "restore_checkpoint"
  }
}

Input Schema

Name	Required	Description	Default
`branch_id`	Yes
`campaign_id`	Yes
`idempotency_key`	Yes
`target_revision`	Yes
`expected_revision`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 18, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, but the description adds meaningful nuance beyond them: the operation is an append of a new revision rather than an overwrite, and 'Never erase history' reinforces the append-only contract. It does not mention permission requirements or how conflicts on expected_revision are handled.

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?

One sentence, front-loaded with the usage precondition, then the behavioral contract. No filler, no redundancy.

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?

The behavioral story is adequate and annotations cover the safety profile, but with five undocumented required parameters and no output schema, an agent still lacks the semantics needed to construct a correct call. Complete on intent, incomplete on invocation.

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

Parameters2/5

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

Five required parameters with 0% schema description coverage, and the description mentions none of them. Critical semantics such as the difference between expected_revision (concurrency guard) and target_revision (snapshot to restore), or the role of idempotency_key, are left entirely unexplained.

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?

States a specific verb and effect: 'append a revision restoring a saved snapshot', and scopes what the snapshot includes (knowledge and world clocks). It is clearly distinguishable from siblings like get_recovery or read_history, though it never names them explicitly.

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?

'Only when the player explicitly requests it' is an explicit, unambiguous trigger condition. It does not, however, name alternatives such as get_recovery or read_history for inspecting state without restoring it, so routing to siblings 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.

Deploy Server