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

Annotations already declare non-read-only, non-destructive, closed-world, so the description's job is to say what actually changes. It does: existing URLs and existing usages stay unchanged, only future uses pick up the new default — a genuinely useful side-effect disclosure beyond the annotations. It does not cover permission requirements or behavior when assetId/version are invalid.

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 front-loaded: the core action and its scope come first, the non-impact statement second, then the alternative workflow. Every clause carries information, though the final imperative ('Conserver cadrage, légende et effets') is a caution rather than a description of this tool's behavior.

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?

No output schema and three required parameters at 0% schema coverage mean the description should explain the inputs, which it largely does not. It does cover intent, side effects, and the sibling workflow well, so an agent knows when to call it but is under-informed about what to pass.

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 description coverage is 0%, so the description must carry all three parameters. It only clarifies the variant concept ('original ou improved'), which the schema enum already enumerates, and gestures at 'version par défaut' without explaining what the version integer means. assetId is never mentioned, leaving the most important identifier undocumented.

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: choosing the default version of a media asset ('original ou improved') for future uses. It immediately distinguishes itself from siblings by naming get_image_versions and edit_live_page/update_page as the path for a different task (replacing an already-inserted image).

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 separates the two cases: this tool changes the default for future uses, whereas replacing an already-inserted image requires get_image_versions then a block update via edit_live_page/update_page with expectedVersion. The only weakness is that 'update_block content' is not an actual sibling tool name, which slightly blurs the routing instruction.

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