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

With destructiveHint=true already flagged, the description adds substantial context beyond annotations: the permission model, the admin-override gating on AI assistants, the fact that the new start must be in the future, and that the new time re-validates against space hours, blackout closures, longest booking, booking window, and the weekly limit. It does not say whether the old slot is freed immediately or whether the change is reversible/undoable, which is the main remaining gap for a destructive mutation.

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 action is front-loaded before permissions and rule inheritance, and every sentence carries operational information. It is on the long side, but the density of constraints (permissions, override gating, booking rules, untrusted-data warning) justifies the length.

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 four-required-parameter mutation with no output schema, the description covers the permissions needed, the override path and how to verify it, the validation rules the new time must satisfy, and a prompt-injection warning about untrusted text. An agent has everything needed to attempt the call correctly or know why it will fail.

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 only 25%, with just workspaceId documented, so the description carries a larger burden. It does clarify that startUtc/endUtc are the new times and that the new start must be in the future and satisfy booking rules, but reservationId goes unexplained and there is no added detail on timezone handling or format beyond the schema's date-time format.

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 opening sentence gives a specific verb pair and resource ('Move or resize one of your upcoming reservations') plus the mechanism ('by giving its new start and end'). It is immediately distinguishable from create_reservation, cancel_reservation, and create_recurring_reservation among the siblings.

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 clearly scopes when this applies (upcoming reservations, own bookings for members, any booking for admins) and names the prerequisite check via get_workspace_info for adminOverride. It stops short of explicitly naming cancel_reservation as the alternative when a booking should not be moved, but the practical routing is clear.

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