turnale

Undo changes

undo_last_change

Destructive

Roll the tournament back. Without to_change_id: restore exactly how it was before the most recent change (tool call or courtside page entry). With to_change_id (an id from get_audit_log): restore to just before that change — it and every later change are discarded in one step, so a burst of unwanted calls unwinds with a single revert. Preview lists exactly what would be discarded; confirm: true applies. To apply exactly what a preview showed, confirm with to_change_id set to the first id in its discarded list — anything that landed in between (a courtside entry) is then listed as discarded instead of silently changing the target. A follow-up plain undo restores what the previous undo discarded.

Input Schema

TableJSON Schema

Name	Required	Description
`confirm`	No	Omit or false: return a preview of what would change. True: apply it.
`request_id`	No	Optional idempotency id — retrying a call with the same id never applies it twice
`to_change_id`	No	A change id from get_audit_log — restore to just before this change, discarding it and everything after it. Omit to undo only the latest change.
`tournament_key`	Yes	The tournament's organiser key (starts with tk_)

Output Schema

TableJSON Schema

Name	Required	Description
`preview`	No	True when this is a preview — nothing was changed
`summary`	Yes	What happened, in one line
`discarded`	Yes	Every change this rollback discards, oldest first
`undone_at`	Yes
`undone_tool`	Yes	Tool behind the earliest discarded change
`undone_summary`	Yes
`discarded_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 12, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

First observedJul 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare destructiveHint=true, and the description earns credit beyond them by disclosing that a burst of changes unwinds in one step, that confirm defaults to a dry-run preview, and that intervening courtside entries are listed as discarded rather than silently shifting the target. This is exactly the behavioral context a destructive tool needs.

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?

Front-loaded with the core action and mode split, and every sentence carries distinct semantics. It is long and dense, with the preview/confirm interaction restated in two places, costing some tightness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is unnecessary, and the description covers the destructive scope, the preview path, and the cross-tool dependency on get_audit_log. Nothing an agent needs to call this safely is missing.

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 100%, so the baseline is 3, but the description genuinely adds: it explains that to_change_id discards that change and everything after it, and that confirm:true must target the first id in a preview's discarded list to reproduce it. It does not, however, discuss request_id idempotency beyond what the schema states.

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 ('Roll the tournament back') and immediately enumerates the two operating modes by parameter. No sibling tool offers reversion, so the agent can identify it unambiguously among the 29 siblings.

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?

Explicitly covers when to omit to_change_id vs when to supply one from get_audit_log, plus the preview/confirm workflow and the unusual case of applying a previewed revert while new changes landed in between. It even names the recovery path ('a follow-up plain undo restores what the previous undo discarded').

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

All turnale tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.