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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds concrete consequence beyond the flags: newer data may be discarded and downtime will occur, which tells the agent what is actually lost and the operational impact. It stops short of covering irreversibility details, approval requirements, or expected duration.

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 short, front-loaded sentences with zero filler; the risk warning follows immediately after the action. Every clause earns 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 high-stakes destructive restore with nine undocumented parameters, no output schema, and no annotations beyond safety flags, the definition is far too thin. It omits the approval gating, target time semantics, and any notion of what the call returns or how long the operation takes.

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?

With 9 parameters and 0% schema description coverage, the description carries the full burden and adds almost nothing: only 'a prior point' loosely gestures at recovery_time_target_unix, with no format (unix epoch), bounds, or meaning. The approval_id and beon_* parameters, plus the environment/connection enums, are entirely unexplained in both schema and description.

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 specific verb and resource ('Restore database to a prior point'), making the operation identifiable. It does not, however, distinguish itself from nearby siblings such as supabase_restore_backup, supabase_restore_project, or railway_restore_volume_pitr, so an agent must rely on the tool name to tell PITR apart from backup restore.

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?

There is no guidance on when to choose PITR over supabase_restore_backup, nor any stated preconditions (approval workflow implied by the approval_id parameter, environment selection, project state). The reader is left to infer usage entirely from the name.

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