Bilinc

rollback

Restore a project to a saved checkpoint by previewing what will change, then executing with a confirmation token to permanently discard memory changes made since that checkpoint.

Instructions

Restore the project to a checkpoint. DESTRUCTIVE in execute mode.

    Two stages, and you must run them in order:

    1. `mode="preview"` is free and changes nothing. It reports what would
       be created, updated, and removed, and returns a short-lived
       `confirmation_token`.
    2. `mode="execute"` requires that token and permanently discards every
       memory created or changed since the checkpoint.

    Execute fails with `state_changed_since_preview` if the project
    changed after the preview, so review the preview and act on it
    promptly rather than reusing an old one. `reason` is required in both
    modes and is written to the audit trail. `limit` (1-500) caps the
    preview list; ignored in execute mode.

Input Schema

Name	Required	Default
`mode`	No	preview
`limit`	No
`reason`	Yes
`snapshot_id`	Yes
`idempotency_key`	No
`confirmation_token`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.6.1Nov 5, 2026

addedInput schema / properties / limit

Added value: +{
+  "default": 100,
+  "title": "Limit",
+  "type": "integer"
+}

Addedv2.1.6Jul 31, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations supplied, the description carries the entire behavioral burden and does so: it flags the operation as DESTRUCTIVE in execute mode, spells out that execute permanently discards every memory created or changed since the checkpoint, and documents the short-lived confirmation_token lifecycle. It also names the exact failure condition and states that reason is written to an audit trail.

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?

The destructive warning is front-loaded, then the two stages are enumerated in execution order with per-mode notes attached to the relevant stage. Every sentence carries operational information; nothing is restated from the schema or padding.

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?

For a destructive state-mutating tool with six parameters and no annotations, this is close to complete: safety profile, sequencing, token dependency, failure mode, and audit behavior are all covered, and an output schema exists so return values needn't be described. The gap is the undocumented idempotency_key and the lack of any note on what snapshot_id refers to or how it is obtained.

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 description coverage is 0%, so the description must compensate, and it explains mode semantics, the required reason and its audit purpose, limit's 1-500 range and its irrelevance in execute, and confirmation_token's requirement in execute. Two parameters are left unaddressed: snapshot_id is only obliquely implied by "checkpoint," and idempotency_key is never mentioned at all.

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?

"Restore the project to a checkpoint" is a specific verb+resource statement, and the two-stage preview/execute framing makes the operation unambiguous. It doesn't explicitly contrast itself with siblings like snapshot, diff, or confirm, so an agent must infer the routing rather than being told.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the mandatory ordering (preview before execute), what each mode is for, and the operational rule to act on a preview promptly instead of reusing an old one. The exclusions are explicit: limit is ignored in execute, and execute fails with state_changed_since_preview if the project moved.

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

Deploy Server