Executer des commandes kernel (brut / lot)

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

The description discloses that batch operations are atomic with a single undo, which is valuable behavioral context. It also explains the template syntax for referencing previous step results, which is important for safe usage. However, it does not mention any risks, side effects, or state mutations beyond undo grouping; with no annotations provided, it could be more transparent about the power and potential destructiveness of kernel commands.

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 reasonably concise and front-loaded with the core purpose and positioning. The batch usage example is detailed but necessary for correct invocation. It could be slightly more structured, but every sentence contributes to understanding the tool's role and usage.

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?

Given there is no output schema and no annotations, the description does a good job explaining the tool's role, batch atomicity, and reference syntax. It points to ae_help for command specifics, which is a practical completeness strategy. However, it doesn't describe return values or error behavior, and the interaction between single command and batch is left implicit.

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 input schema already provides 100% coverage with descriptions for every parameter. The description adds meaningful context for the batch parameter by explaining the {{index.chemin}} and {{prev.xxx}} syntax, which goes beyond the schema. However, it doesn't clarify how args, command, and batch interact (e.g., whether command/args is mutually exclusive with batch), which would add further value.

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 it provides direct access to all kernel commands, either single or batch, and positions it as the most powerful tool covering everything other tools do plus edge cases. It distinguishes itself from specialized siblings by being the generic/raw access tool. It falls short of a 5 because it doesn't explicitly name a sibling it should be preferred over, though the contrast is implied.

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 explicitly says this tool is the most powerful and covers everything other tools do plus unanticipated cases, which tells the agent when to use it: for raw or batch operations not covered by specialized tools. It also directs to ae_help for the command list and arguments. It lacks explicit when-not-to-use guidance and alternatives, but the sibling context makes the division of labor fairly clear.

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