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

Annotations already flag destructiveHint=true, but the description adds value beyond them: irreversibility ('Nothing restores from it again'), the collateral destruction of vault objects, and the two refusal states. It also declares the required permission, which no structured field provides.

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?

Front-loads DESTRUCTIVE and packs preconditions and permission into a few short sentences with no filler. The parenthetical CLI-equivalence note is marginal for an MCP agent, the one small bit of text that does not fully earn 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 mutation with no output schema, the description covers everything an agent needs: irreversibility, what else is destroyed, refusal conditions, and auth requirements, with parameters fully specified by the schema. Nothing material 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?

Schema coverage is 100%, so cluster_id/cluster_name/stack_name/restore_point_id are fully documented in the schema itself, including the hint that the id comes from list_restore_points. The description adds only the implicit notion that the restore point belongs to a stack/belt vault, so baseline 3 applies.

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 precise verb+resource ('Delete a restore point') and adds the non-obvious scope of the operation ('sweep its objects from the backup vault'). This distinguishes it from the sibling family (get_restore_point, list_restore_points, create_stack_restore_point, restore_restore_point_in_place) without the agent needing to open schemas.

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 concrete preconditions for refusal ('still being created, or one a run is using') and the permission gate ('Requires backups.manage'), which tells the agent when the call can and cannot succeed. It never names the sibling to use instead for restoration (restore_restore_point_in_place), so it stops short of explicit alternatives.

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