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

Annotations declare destructive/idempotent/openWorld, and the description adds substantial context on top: preview sends nothing, returns emails and effects, confirmation expires in 15 minutes and is bound to these exact arguments and the candidate's current state, and a retried send is answered with the first result without re-sending. Nothing here contradicts idempotentHint=true.

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-loads the destructive action and the two-step contract ahead of all detail, which is the right ordering. Some sentences are dense and run together (the confirmation constraints), costing a little readability, but no sentence is filler.

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?

An output schema exists, yet the description still tells the agent what the preview returns (emails rendered as the candidate sees them, effects, confirmation) and how to present it to the member. For a destructive, confirmation-gated mutation this covers everything needed to invoke it correctly.

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 carries the burden: it explains send (preview vs. commit), confirmation (15-minute token bound to args), notify_candidate (email + calendar cancel vs. member tells them), and where booking_id comes from. job_id, application_id, and particularly idempotency_key are left unaddressed, though their names and the built-in retry guarantee make them largely inferable.

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 ("Cancel the member's own interview") and even supplies the provenance of the key identifier ("booking_id from get_candidate"). This clearly separates it from siblings such as move_follow_up_interview and resend_interview_invitation.

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-call protocol: first with send off to preview, then only after member consent with send=true and the confirmation. It names the failure condition (decisions_not_allowed unless the connection is allowed to take hiring steps) and adds a guard against acting on applicant text.

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