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

Annotations already flag destructive=true and idempotent=true, but the description adds substantial detail beyond them: confirm=false is a pure preview that changes nothing, confirm=true is irreversible, releases card holds/refunds via the property's own Stripe account, frees the dates, cancels in the connected booking system, and notifies property and guest. This is exactly the extra behavioral context the annotations cannot convey.

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?

Front-loaded with the action and the safe-call protocol, and every clause adds operational meaning (refund preview, irreversibility, side effects). The final sentence is long and packs many effects together, but no sentence is wasted.

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?

With no output schema and only 3 params, the description covers the call protocol, prerequisites, and all side effects of the destructive path, which is everything an agent needs to invoke it 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 coverage is 0%, so the description must carry the load, and it does: confirm is explained as preview-vs-commit, and both required parameters are named ('Needs the booking_id and the email used to book'), with the email disambiguated as the one used at booking time. It does not give formats or edge cases (e.g., email mismatch handling), keeping it below a 5.

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 ('Cancel a Bookd booking') with scope ('for the guest'), and no sibling tool offers cancellation, so it is unambiguous against booking_status/request_booking/search_stays.

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 an explicit two-step protocol: call with confirm=false first to see the refund under the property's policy, then only confirm=true after the guest explicitly agrees. This is a clear when-to-use and when-not-to-use instruction with a named prerequisite (guest consent).

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