Skip to main content
Glama

Undo an AI agent change

undo_change
DestructiveIdempotent

AI Agents: Use when the customer asks to undo a change the assistant made. It puts the values from before back, only while the record still holds what was written, so newer work is never overwritten. A new record cannot be undone: nothing is ever deleted. Ask the customer before calling it. Not for stopping an automation (use set_automation_status).

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": {
      "change_id": "<change_id>"
    },
    "name": "undo_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
change_idYesThe change id, as apply_proposal or list_changes returns it.

Output Schema

NameRequiredDescriptionDefault
atYes
idYes
kindYes
noteNo
typeYes
errorNo
labelYes
fieldsYes
statusYes
canUndoNo
recordIdYes
systemIdNo
operationYes
proposalIdNo
systemNameNo
sendsMessageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the conditional compare-and-swap semantics: the undo only applies while the record still holds the written value, so newer work is never overwritten, and creation cannot be undone because nothing is deleted. That reconciles the destructiveHint=true flag with the actual effect. It stops short of naming failure modes or what the response reports on a rejected undo, which the output schema may cover.

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?

Four short sentences, front-loaded with the usage trigger before the semantics and the exclusion. Every sentence carries decision-relevant information with no filler.

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?

An output schema exists, so return values need not be explained, and the description covers the safety precondition and effect semantics thoroughly. The only remaining gap is how a suppressed undo (record changed since) is surfaced, which the output schema likely handles.

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 change_id parameter already documents its source ('as apply_proposal or list_changes returns it'). The description adds no further meaning about the identifier or its format, so the baseline 3 applies.

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 a change the assistant made') and scopes it to the AI-agent context. It also names the sibling it is not (set_automation_status), so an agent can route without opening either schema.

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?

Explicit trigger ('when the customer asks to undo a change'), explicit exclusion ('Not for stopping an automation'), a named alternative, and a prerequisite ('Ask the customer before calling it'). Little 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources