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

Annotations already declare destructive=true and non-idempotent, but the description goes well beyond them: it spells out that current data is replaced and lost, the exact confirm-string requirement, the refusal-until-force condition, the unrecoverable database-types exception, and the required backups.operate permission. This is unusually complete disclosure for a destructive operation.

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 severity marker and core effect are front-loaded in the first clause, and the remaining sentences each carry load-bearing constraints (confirm, force, database refusal, permission). It is dense but slightly sentence-heavy; nothing is truly wasted, though it could be tightened.

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?

There is no output schema, so the description carries the return/behavior burden and does so by enumerating the refusal outcomes an agent will actually encounter and how to respond to them. For a destructive, non-idempotent tool with 6 parameters, this covers everything needed to call it correctly and safely.

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 100%, so the schema already documents force, confirm, restore_point_id and the cluster identifiers, and the description largely restates them (confirm exactness, complete-restore-point requirement). It adds marginally by linking force to the 'data changed since restore point' condition, but does not add syntax or format detail the schema lacks.

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 states a precise verb and resource ('Restore a stack's data in place from one of its restore points') and immediately scopes it with the in-place semantic that separates it from sibling restore-point tools like create_stack_restore_point, get_restore_point, list_restore_points and delete_restore_point. The 'DESTRUCTIVE' lead makes the operation's nature unambiguous at a glance.

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 real when/when-not guidance: confirm must be the stack's own name, force=true is required if the data changed, and the call is refused outright for unsupported database types with an explicit instruction not to retry. It stops short of naming the sibling MCP tools (list_restore_points, delete_restore_point) as alternatives, so it is not fully routing-aware.

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