logoff_vdi_session

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

Annotations already declare destructiveHint=true and non-idempotency, but the description adds real behavioral context beyond them: the two-phase dry-run/confirm flow, the side effect of profile write-back, the refusal when a user cannot be read, and the fact that calls are audited.

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 write/destructive marker and the core action, then the targeting options, then the safety protocol. Every sentence carries information an agent needs; nothing is padding.

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?

No output schema exists, yet the description explains what a non-confirming call returns (session ids, count, affected users), what confirmation does, and the failure case, which is exactly the information an agent needs for a destructive, non-idempotent operation.

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 description coverage is 100%, so the baseline is 3, but the description adds the alternative-selection relationship between session_ids and user that the schema states only in isolation, plus the meaning of a bare call in terms of the confirm parameter's effect on returned blast_radius.

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?

Specific verb+resource ('Force-logoff Horizon session(s)') with the destructive nature flagged up front via the [WRITE] tag. It also implicitly distinguishes itself from the read-only siblings and from disconnect_vdi_session by stating it 'kicks the user' and triggers profile write-back, so an agent can tell it apart from the other session tools.

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?

Explicit targeting rules (session_ids OR user), an explicit default dry-run path, and an explicit escalation rule: show blast_radius to the user, wait for their decision, and never set confirm=True on your own. It even pre-empts a likely agent failure mode (acting on a stale earlier instruction).

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