preparer_retour_arriere

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

With no annotations, the description carries the full burden and does meaningful work: it warns that the rollback 'Peut écraser les modifications postérieures des mêmes éléments', discloses that partial/uncertain runs are refused, and points to a preview step. It stops short of stating permission requirements or clarifying that this only builds a plan rather than executing it, leaving some behavioral gaps.

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?

Dense but well-structured: purpose first, then the overwrite warning, then the refusal/alternative clause. Every clause carries information, though the warning and preview instruction could be tightened.

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 one-parameter tool with no output schema or annotations, the description covers purpose, destructive-risk warning, refusal conditions, and the sibling alternative. It lacks permission/auth context and does not explain what the generated plan/preview contains, but the core decision-relevant information is present.

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 coverage is 0% and the single run_id parameter is undocumented in the schema. The description only implicitly conveys that run_id refers to 'cette exécution' whose prior backup is restored, adding modest meaning but not resolving format or which executions are eligible.

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+resource: 'Préparer un plan pour restaurer la sauvegarde avant cette exécution et supprimer ses créations connues.' It distinguishes itself from the sibling preparer_restauration and journal_execution, so an agent can tell this apart from the generic preparer_plan/preparer_restauration 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?

Explicitly names the exclusion ('Refuse les exécutions partielles/incertaines') and routes the agent to the correct alternative ('consulter le journal et utiliser preparer_restauration'). It also directs the agent to read the preview before proceeding, leaving little to inference.

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