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

Annotations already declare non-read-only, destructive and idempotent, and the description goes meaningfully beyond them: it names the exact stage transitions for each outcome, discloses the refusal condition for stale/cancelled interviews, and explicitly states no email is sent ('Emails nobody'). That is exactly the mutation side-effect information 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?

Four short sentences, front-loaded with the action and outcome domain, then transitions, then the refusal rule, then the side effect. Every clause adds information; nothing is repeated from the schema or annotations.

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, so return values need no explanation, and the state-machine behavior is well covered. However, for a 4-required-parameter mutation with zero schema description coverage, the description leaves the identifier parameters wholly unexplained, which is a real gap for correct invocation.

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 full burden, yet it only clarifies the outcome domain ('completed or a no-show'). The three identifiers — job_id, application_id, booking_id — are never described in either the schema or the description, leaving the agent to guess their provenance and 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?

States a specific verb (record) and resource (the member's own interview) with the exact outcome domain (completed / no-show) and the resulting stage transitions. It also distinguishes itself from the booking tools by pointing to get_candidate for the underlying bookings, so an agent can separate it from book_follow_up_interview or cancel_follow_up_interview.

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 the prerequisite path ('a follow-up: get_candidate lists the bookings') so the agent knows where booking_id comes from, and states a clear exclusion rule ('An interview that is already over or cancelled is refused'). No explicit contrast with cancel tools, which keeps it short of a 5.

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