invalidate_transactionUnconfirm a confirmed transaction to return it to unconfirmed status for editing or deletion; record why and what replaces it for traceable corrections.
Invalidate (unconfirm) a confirmed transaction. Returns it to unconfirmed status for editing or deletion. RPS § 10: corrections must stay traceable — record why and what replaces it.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Object ID |
Changes observed during successful MCP inspections.
v0.29.2Input schema / additionalPropertiesAdded value: +falsev0.18.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, which the description does not contradict. The description adds meaningful domain context: the resulting state is 'unconfirmed' for editing/deletion, and it cites RPS § 10 requirements to record the reason and replacement. This goes beyond annotations, though it does not disclose side effects on linked records.
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 short sentences, front-loaded with the primary action and outcome. The RPS citation is slightly terse and might be unclear without domain knowledge, but it contributes regulatory context rather than waste.
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?
With one fully documented parameter, no output schema, and safety annotations present, the description is largely complete for this simple mutation. It omits the response shape and any cascading effects, but those gaps are minor given the tool's narrow scope.
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 100%: the single 'id' parameter is fully described as 'Object ID' with a type constraint. The description does not restate or expand on parameter meaning, which is acceptable under the baseline-3 rule when the schema carries that burden.
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?
States a specific verb and resource ('Invalidate a confirmed transaction') and immediately clarifies the domain-specific meaning with '(unconfirm)'. Sibling tools like invalidate_journal and invalidate_sale_invoice share the verb, so this correctly identifies the transaction-specific effect: returning to unconfirmed status.
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 implies when to use it ('for editing or deletion') but does not explicitly differentiate from delete_transaction or update_transaction, nor does it state preconditions other than 'confirmed'. There is no mention of when invalidation is inappropriate versus a direct delete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.