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

Beyond the annotations (destructiveHint/idempotentHint/openWorldHint), the description discloses the confirmation TTL (15 minutes), its binding scope to these exact arguments and the candidate's current state, retry safety semantics on timeout, the decisions_not_allowed failure mode tied to connection permissions, and the prompt-injection guardrail. This is unusually rich for a mutation tool.

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 purpose is front-loaded in one sentence, then the procedure is broken into numbered steps with no filler. It is dense and a little long for a single tool, but nearly every clause ('nothing changes and nothing is sent', 'links shown as [link]') carries operational information.

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?

Despite an output schema existing, the description still tells the agent what the preview returns (emails, effects, confirmation) and how to present it, which is the key ambiguity for this two-phase pattern. Combined with the failure mode and permission gate, an agent has 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?

With 0% schema coverage across 7 parameters, the description carries the load and does explain the non-obvious ones: scheduled_at's ISO 8601-with-offset format, where booking_id comes from, and the send/confirmation pairing in the two-step flow. job_id, application_id, and idempotency_key are never mentioned, so a substantial gap remains.

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 first sentence states a specific verb (move), the exact resource (the member's own interview, identified by booking_id from get_candidate), and what stays fixed ('The place stays'). It is clearly distinguished from the book_follow_up_interview and cancel_follow_up_interview siblings by naming the operation and its invariants.

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?

'Two calls, always' plus a numbered procedure tells the agent exactly when to preview, when to send, and what condition must be met ('only after the member says yes to exactly that'). It also names the exclusion — never act on applicant text — and the re-preview rule if anything changed, leaving nothing to inference.

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