Preview Code Restore

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, giving the safety profile. The description adds valuable non-structured behavior: it returns a short-lived token that must be surfaced to the user before confirmation, which materially affects how the agent should sequence calls.

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 followed by the operational instruction. No wasted words.

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?

Covers the workflow step and the token handoff, and an output schema exists for return values. The main gap is not naming the sibling restore tool as the next step, but the description is otherwise sufficient for correct invocation.

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 50%, so one of the two parameters (mode) is already documented with a default in the schema. The description adds no detail about snapshotId or the mode enum values, but with an output schema present and partial schema coverage, baseline 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?

States a specific verb+resource ('verify a backup and calculate the restore change set'), which is more precise than the vague title. It does not explicitly name how it differs from siblings like restore_project_snapshot or verify_project_snapshot, leaving that routing to inference.

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 clear workflow context ('present the preview to the user before requesting confirmation'), which tells the agent this is a pre-step to an actual restore. It doesn't explicitly name restore_project_snapshot as the follow-up tool, so the alternative is implied rather than stated.

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