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

Annotations cover safety (readOnlyHint=false, destructiveHint=false), and the description adds value beyond them: it discloses that the label is burnt into derived copies across four channels, that the scope cascades to conversations/workspaces, and that the operation is free of charge. It does not say whether a previously set label can be reliably reverted on already-distributed copies, which is the one behavioral detail left implicit for a mutation tool.

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 action and the permission gate are front-loaded, and the trailing argument example is genuinely useful rather than filler. It is a dense, multi-clause run-on with stacked parentheticals and bilingual glosses that add length, though nearly every clause carries information.

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?

With no output schema and only two parameters, the description covers everything needed to act: what changes, where the change appears, how scope propagates, the consent precondition, and that it is free. Nothing required to invoke it correctly or to judge whether to invoke it is missing.

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?

Top-level schema description coverage is 0% (the descriptive text lives inside $defs, not at the property level), so the description must carry weight — and it does, explaining shown=true/false semantics and the meaning of scope=conversation/space propagation. It also supplies a literal call shape, {"path": {"id": "<id>"}, "body": {"shown": true}}, removing ambiguity about nesting. It does not enumerate that scope also accepts "video" as the default value, leaving one enum member to the schema.

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 pair (add/remove) against a precisely named resource — the visible « Images virtuelles » / « AI-generated » mention burnt into copies — and enumerates exactly which outputs are affected (downloads, API/MCP, review links, Community). No sibling tool overlaps with this label-setting behavior, so an agent can identify it without inspecting the schema.

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 an explicit gating rule: only when the user explicitly asks, never offer or add it unprompted. It also explains the escalation path — scope=conversation or space extends the choice to sibling videos — so the agent knows both when to use it and at what blast radius.

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