Skip to main content
Glama

live_history

Destructive

Undo or redo one recorded live_edit batch in the same Proteus document, validating the current token, stopped simulation, and matching semantic history before applying changes.

Instructions

Undo or redo exactly one recorded MCP live_edit batch in the same native document. Requires current live_read token, stopped simulation and matching semantic history. External edits, no-op or partial batches invalidate history. Does not emulate keyboard input.

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": {
      "session": "<session>",
      "expected_token": "<expected_token>",
      "action": "<action>"
    },
    "name": "live_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
sessionYes
expected_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real value on top: the token requirement, the stopped-simulation requirement, and the specific events that invalidate history. It also excludes a common wrong assumption (keyboard emulation), which shapes how an agent should reason about the effect.

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?

Four short sentences, front-loaded with the core action and followed by preconditions and invalidation rules. Every sentence carries information, though 'matching semantic history' is left undefined and reads as compressed jargon.

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 three-parameter mutation with no output schema, the description covers prerequisites and failure modes well. It stops short of describing what state the document and history are left in after a successful undo or redo, and gives no hint about error signaling when history is invalidated.

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 0%, so the description must compensate. It clarifies 'expected_token' as the current live_read token and constrains 'action' to a single-batch undo/redo, but 'session' is never explained and no format or source for the token is given.

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 pair (undo/redo), a precisely scoped resource (exactly one recorded live_edit batch), and the domain constraint (same native document). An agent can distinguish this from live_edit purely from the description.

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 concrete preconditions: current live_read token, stopped simulation, and matching semantic history, plus the conditions that invalidate history (external edits, no-op or partial batches). It does not explicitly name an alternative tool for making new edits, so routing is implied rather than stated.

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