infomaniak_undo

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

The description discloses the two-phase commit behavior: 'returns a plan first, then applies the undo on the second call'. This goes beyond the annotations, which only indicate destructive and non-idempotent behavior. It also notes the 'when reversible' limitation. However, it does not explain the content of the plan or the need for a confirmation token, leaving some ambiguity.

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?

The description is two sentences, with the primary purpose stated immediately. Every word earns its place: it names the action, scope, and key behavioral caveat. There is no fluff or redundant restatement of the tool name or annotations.

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?

The description explains the core two-phase mechanism but omits important operational details, such as how to obtain a history_id (e.g., via infomaniak_history) and what the plan contains. Given the tool's destructive nature and the presence of an output schema, a bit more guidance would make it fully self-sufficient. Still, it provides adequate high-level context for a capable agent.

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?

The schema has 0% description coverage, and the description does not compensate. While 'history_id' and 'confirmation_token' are inherently suggestive, the description fails to explain their roles, especially that history_id identifies the action to undo and confirmation_token is presumably obtained from the first-phase plan. The two-phase mention hints at the token but does not explicitly define it.

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 tool's function: 'Reverse a destructive action recorded in the session history'. The verb 'Reverse' is specific, the resource is a destructive action, and the scope is limited to session history and reversibility. This distinguishes it from sibling tools like infomaniak_history or direct delete tools.

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 the tool: after a destructive action, when it's recorded in session history and reversible. However, it does not explicitly mention alternatives (like restoring from trash) or exclusions (e.g., non-reversible actions). The 'when reversible' qualifier provides some guidance but not a full usage policy.

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