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

Annotations only declare destructive/not-readOnly; the description goes far beyond, disclosing that `confirmed:false` is a no-op, that absent `cancellationFee` means "not reported" rather than zero, that refunds are separate, and the full `failureReason` taxonomy including the do-not-retry `SUPPLIER_NOT_CONFIRMED` case. Session and guest-session constraints are also surfaced.

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?

It is a single dense block, but front-loaded with the action and required params before the safety flow and edge cases. Nearly every clause carries information, though the `email` magic-link mechanics are explained here and again in the schema, and parentheses make it heavier than ideal.

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 terminal action, the description covers authentication prerequisites, the confirmation gate, success payload (`cancellationFee`, `success`, `message`), and every failure branch. No output schema exists, yet return semantics are described sufficiently for correct follow-up behavior.

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 the baseline would be 3, but the description adds real meaning beyond it: the non-obvious no-op semantics of `confirmed:false`, the fallback role of `email` when no session exists, and the optionality of `reason`. Only `sessionToken` behavior is left entirely to the schema.

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 and resource ("Cancels an existing booking") and immediately frames the scope via the required `bookingId`, clearly separating it from siblings like `get_booking_details` and `check_cancellation_policy`. An agent can identify both the action and the object without opening the schema.

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?

Explicitly prescribes the two-step flow (`confirmed:false` first, then `confirmed:true`) and names `get_booking_details` as the place to read fees before calling. It also gives an alternative path for unauthenticated sessions (`email` magic link) and instructs the agent to confirm with the user before the terminal call.

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