Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

rollback_import

Destructive

Rolls back ONE import batch: deletes the tasks that this batch CREATED and that nobody has modified since. Keeps — and DECLARES with its reason — any task edited since the import, and any task still referenced (subtask or dependency) by a task that survives. Does NOT RESTORE what an onExisting: "update" batch modified. dryRun is TRUE by default: the call returns what would be deleted (an edit that arrived between this plan and the deletion is not detected). Resumable: at most 500 deletions per call; remaining says whether any are left — a new call with the same importId continues. DESTRUCTIVE and irreversible with dryRun: false. Each call that deletes leaves ONE aggregated event in the activity log (import.rolled_back: tasks deleted, tasks spared).

Input Schema

NameRequiredDescriptionDefault
dryRunNoDefault TRUE: returns what would be deleted or kept, WITHOUT deleting anything. `false` to delete.
importIdYesThe batch to roll back (`list_imports`, or the `importId` returned by `import_tasks`).
expectedProjectIdNoUUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / dryRun / description
      Previous value: -"Défaut TRUE : rend ce qui serait supprimé ou gardé, SANS rien supprimer. `false` pour supprimer."New value: +"Default TRUE: returns what would be deleted or kept, WITHOUT deleting anything. `false` to delete."
    • changedInput schema / properties / expectedProjectId / description
      Previous value: -"UUID du projet visé par CET appel. Cible RÉELLEMENT ce projet au lieu du projet de session. Refusé sans rien modifier si l'accès n'est pas accordé."New value: +"UUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted."
    • changedInput schema / properties / importId / description
      Previous value: -"Le lot à annuler (`list_imports`, ou l’`importId` rendu par `import_tasks`)."New value: +"The batch to roll back (`list_imports`, or the `importId` returned by `import_tasks`)."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Far beyond the annotations, it discloses what is deleted, what is spared and why it is declared with a reason, the race condition where an edit between plan and deletion goes undetected, the 500-deletion cap with a `remaining` continuation signal, irreversibility at `dryRun: false`, and the single aggregated `import.rolled_back` activity-log event per call. Annotations only carry the destructive flag; the description supplies the operational detail.

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?

The core semantics (what is deleted, what is kept) are front-loaded and every sentence carries a distinct fact rather than filler. It is a dense paragraph that is longer than most, though not padded.

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?

For a destructive, non-idempotent, resumable mutation with no output schema, the description covers return semantics (dry-run output, `remaining`), retry/continuation behavior, and side effects (activity-log event). 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 adds meaning the schema does not: the default-true dry-run is framed as 'returns what would be deleted or kept' and the plan/deletion race gap is called out. `importId` resumability ('a new call with the same importId continues') is also useful context beyond the raw field description.

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?

The description states a precise verb and resource — 'Rolls back ONE import batch' — and immediately defines scope: tasks this batch CREATED that nobody has modified. It also names what it will not do (does NOT RESTORE what an `onExisting: "update"` batch modified), which separates it cleanly from import_tasks and list_imports.

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?

It tells the agent where the importId comes from (`list_imports` or the value returned by `import_tasks`) and that `dryRun` defaults to true, so the safe path is implied. It stops short of naming when a different tool would be the right choice (e.g., per-task deletion tools in the sibling list), so it is clear context without explicit alternatives.

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

All OrgGen AI toolsInspect
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.

Resources