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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral detail beyond annotations: the model keeps its current name after restoration, which an agent would otherwise have to guess. It does not spell out whether the overwritten state is retained as a new version, but the destructive hint already signals risk.

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 tight sentences, front-loaded with the core action and then the undo recipe. Every clause carries useful information with no repetition of the schema or title.

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 two-parameter mutation tool with annotations covering the destructive nature and no output schema, the description is nearly complete: it names the action, the name-retention behavior, and how to pick the right version. A slight gap is that it does not clarify whether the pre-restore state is preserved as a new version.

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 100%: both modelId and version are documented in the schema, including that version comes from list_versions. The description's mention of list_versions reinforces the schema but does not add syntax or meaning beyond it, so the baseline of 3 is appropriate.

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 uses the specific verb 'restores' with the resource 'the model' and target 'an earlier version,' and adds the non-obvious qualifier 'keeping its current name.' It also names list_versions as the source of the version number, clearly distinguishing this tool from edit_model or create_model.

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 explicit operational guidance for undoing a change: restore the version saved just before it, as listed by list_versions. This tells the agent both the scenario and the prerequisite source of the version number, though it does not explicitly state when not to use this tool versus edit_model.

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