disconnect_vdi_session

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

Annotations mark it non-read-only and destructive, but the description adds what those hints cannot: a two-phase dry-run/confirm protocol, that state is preserved (softening the destructive read), that unreadable-user sessions are refused, that the call is audited, and the contents of the blast_radius payload. It does not contradict destructiveHint=true — it clarifies the degree of disruption.

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 marker and the core verb, then broken into short lines for targeting, dry-run behavior, and the safety instruction. Every sentence carries operational weight; nothing 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?

Despite no output schema, the description explains exactly what a bare call returns (session ids, count, affected users) and how to proceed, which is what an agent needs for a zero-required-parameter, safety-gated mutation tool.

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 100%, so the baseline is 3, but the description adds the OR relationship between session_ids and user and reinforces confirm's default semantics beyond the field-level text. It doesn't add syntax detail for the user substring match, but the choice logic is meaningful extra.

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 ('Disconnect Horizon session(s)') plus the key semantic that distinguishes it from siblings: state is preserved and the user can reconnect, explicitly contrasting with logoff_vdi_session. An agent can pick between the two session-terminating tools without reading further.

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 explicit selection rules (by session_ids OR user), the dry-run default, and the confirm=True gate, plus an operational instruction to show blast_radius and wait for the user's decision before confirming. It even names a specific misuse pattern to avoid ('do not set confirm=True because the user asked earlier').

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