Skip to main content
Glama

Restore checkpoint

restore_checkpoint
DestructiveIdempotent

Restore project files to a checkpoint from list_checkpoints. git_sha null resets to the project's very first commit, which discards all later work: only on the human's explicit request.

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": {
      "git_sha": "<git_sha>"
    },
    "name": "restore_checkpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
git_shaYesCheckpoint sha; null = the first commit (wipes later work)
files_onlyNo
project_idNoProject id (or use session from use_project)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / git_sha / description
      Added value: +"Checkpoint sha; null = the first commit (wipes later work)"
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, so the description earns credit for specifying exactly what gets destroyed: null git_sha 'resets to the project's very first commit, which discards all later work.' That is concrete blast-radius detail the boolean flag cannot convey. It still doesn't say whether the restore is undoable or how uncommitted/untracked files are treated.

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?

Two short sentences with the destructive consequence front-loaded before the permission caveat. Every clause carries information an agent needs; nothing is padding.

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?

For a destructive mutation with no output schema, the description covers the sha semantics and the human-approval rule, but leaves 'files_only' entirely undefined and says nothing about reversibility or the state of uncommitted changes. Adequate to prevent the worst mistake, not complete enough for confident invocation.

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?

At 67% schema coverage, git_sha and project_id are already documented in the schema, and the description mostly restates the git_sha semantics (adding the emphasis on discarding work). The 'files_only' parameter has no description in either the schema or the description, leaving a real semantic gap that the description fails to compensate for.

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 precise verb and resource ('Restore project files') and names its prerequisite source ('a checkpoint from list_checkpoints'), which cleanly separates it from the sibling listing tool and from file-editing tools like edit_file. An agent can identify the operation and its input origin without opening the schema.

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 guardrail: null git_sha 'only on the human's explicit request', which is a genuine when-not condition, and points at list_checkpoints as the way to obtain a valid sha. It stops short of stating general when-to-use-vs-alternatives guidance (e.g. restoring vs. editing files forward), so it is strong but not complete.

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.

Resources