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

Annotations already cover the safe read-only, closed-world profile, and the description adds real value beyond them: it returns actual images plus a coverage report, explicitly does NOT validate interactions, and expectedVersion pins the render to specific edits (a concurrency guarantee). It omits image size/count ceilings and what happens when maxImages is exceeded.

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 tightly packed: every clause carries a distinct constraint (mode, targeting, source, surface, return contract, versioning) with no filler, and the core purpose is front-loaded. It is written in French while the tool name, schema and annotations are English, which hurts scanability for an English-speaking agent.

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 an 11-parameter, non-destructive capture tool with no output schema, the description does well on return behavior and versioning but leaves the agent without guidance on tile/pagination mechanics (offset + maxImages interaction) and tileHeight, which materially change the call. Adequate but with real gaps.

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 the load; it explains mode, source, surface, devices, sectionRefs/snapshot and expectedVersion meaningfully. However, pagination-critical parameters offset, maxImages and tileHeight, plus pageId, get no semantic explanation, and 'pagination explicite' is asserted without saying how offset drives it. Partial compensation only.

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 opening states a specific verb and resource ('Capturer visuellement toute la page Outil en un seul appel') plus device scope and mode options, so an agent knows exactly what it does. It does not name a distinguishing boundary against visually similar siblings such as inspect_page_region or show_preview, which keeps it below a 5.

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?

It gives clear selection rules: default is a per-format overview, 'mode tiles' for real-size detail with explicit pagination, and sectionRefs + snapshot to retarget several sections after a batch of corrections. Source (draft/published) and surface (designer/preview) contexts are also stated. No exclusion against alternative tools is offered, so no 5.

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