transaction_openOpen an undoable transaction on the active document to group changes, then commit to keep or abort to roll back. Nested transactions close in reverse order.
Begin an undoable transaction on the active document. Pair with transaction_commit (keep the changes) or transaction_abort (roll back). Transactions nest — the most-recent open is committed/aborted first.
| Name | Required | Description | Default |
|---|---|---|---|
| label | No | Transaction |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description adds value by explaining the undoable nature, the pairing semantics, and the nesting behavior (most-recent open is committed/aborted first). It does not contradict annotations. It could add more about what happens to the active document if no transaction is open, but the core behavioral traits are well disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with no waste. The core action is front-loaded, the pairing is stated immediately, and the nesting rule is a single clarifying sentence. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one optional parameter and no output schema, the description covers the essential usage: what it does, how to pair it, and nesting behavior. It doesn't mention error cases (e.g., calling without an active document) or whether the label appears in UI, but these are minor for a transaction opener. The sibling list is huge, but the description names the two relevant siblings directly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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. The description does not explicitly explain the 'label' parameter, but the parameter has a default and is optional. The description's focus on transaction semantics is more important than the label. A 4 is appropriate because the description adds meaningful context about the transaction lifecycle, though it doesn't detail the label's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Begin'), the resource ('an undoable transaction on the active document'), and the pairing with transaction_commit/transaction_abort. It distinguishes itself from siblings by naming the exact counterpart tools and their effects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use this tool (to begin an undoable transaction) and names the alternatives/companions: transaction_commit to keep changes, transaction_abort to roll back. It also explains nesting behavior, which guides correct usage order.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.