save_scene

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

Annotations already declare destructiveHint=true, and the description adds real context beyond them: the previous version is copied into <dossier_sorties>/sauvegardes before overwrite, giving a recoverability story. It does not state the effect on a never-saved scene or whether backup can be suppressed, but the risk profile is well communicated.

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?

Two short sentences, zero filler, with the destination default stated first and the destructive warning second. Every clause earns its place.

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 destructive two-parameter mutation with an output schema available for return values, the description covers the target file, the backup side effect and the permission threshold. The only meaningful gap is the un-documented 'backup' toggle and behaviour on a never-saved scene.

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%, so the description must carry the parameters and only partially does: it explains the default target file (clarifying that 'path' is optional) and describes the backup copy behaviour, but never ties that behaviour to the 'backup' boolean or says that setting it false disables the safety copy.

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 and resource ('Enregistre la scène') plus the default destination ('par défaut sur son fichier .bip actuel'), so an agent knows exactly what is written and where. It does not explicitly distinguish itself from neighbours like save_material_to_library, but the scene-vs-material scoping is unambiguous.

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?

Gives a hard usage constraint: overwriting the user's file is permitted 'seulement à sa demande explicite', which is exactly the gating condition an agent needs before invoking a destructive save. No alternative tools are named, which keeps it out of 5 territory.

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